© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 77808
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific fixed username string, especially when it appears in requests to manipulate or analyze that string (e.g., reverse, space out, spell, or count it).

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     slow
    -0.07
     Cleaner
    -0.07
    Desc
    -0.07
     Slow
    -0.07
    ena
    -0.06
    _Timer
    -0.06
     Buf
    -0.06
    宏
    -0.06
    .atomic
    -0.06
     V
    -0.06
    POSITIVE LOGITS
     patter
    0.08
     swe
    0.07
     interceptions
    0.07
     טיול
    0.07
    מבקר
    0.06
     disorder
    0.06
     degrees
    0.06
     PhpStorm
    0.06
    갯
    0.06
    ┙
    0.06
    Activations Density 1.261%

    No Known Activations