© 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. 19-RESID-POST-AA
    11. 2001
    Prev
    Next
    INDEX
    Explanations

    type

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     thư
    -0.07
     Sanctuary
    -0.07
    Bond
    -0.07
    .tables
    -0.07
    berapa
    -0.07
     identifies
    -0.06
    用人
    -0.06
    _Style
    -0.06
     Każdy
    -0.06
     MISSING
    -0.06
    POSITIVE LOGITS
    .mixer
    0.07
    PEG
    0.07
    	java
    0.07
    Ay
    0.07
    战士职业
    0.07
    国足
    0.07
    .charAt
    0.07
    语言
    0.07
    펐
    0.07
    WT
    0.07
    Activations Density 0.003%

    No Known Activations