© 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. 68368
    Prev
    Next
    INDEX
    Explanations

    say "Collect"

    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
     compassion
    -0.07
    ﱰ
    -0.07
     Gabriel
    -0.06
    -posts
    -0.06
    ଆ
    -0.06
    Descri
    -0.06
     nuis
    -0.06
    _pipe
    -0.06
    𝒸
    -0.06
    /umd
    -0.06
    POSITIVE LOGITS
    新浪财经
    0.07
    仟
    0.07
     comfortably
    0.07
    会展
    0.07
    Presentation
    0.07
       ↵
    0.07
    说什么
    0.07
    比率
    0.07
    𬍛
    0.07
     
↵
    0.06
    Activations Density 0.009%

    No Known Activations