© 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. 76402
    Prev
    Next
    INDEX
    Explanations

    Forum/blog type texts

    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
    构
    -0.07
    ﯛ
    -0.07
     circa
    -0.07
    /terms
    -0.07
     cornerback
    -0.07
    armor
    -0.06
    .Score
    -0.06
     Uttar
    -0.06
    letter
    -0.06
    豺
    -0.06
    POSITIVE LOGITS
     sua
    0.08
     friendly
    0.07
    Prob
    0.07
    _B
    0.07
    把自己的
    0.06
    上的
    0.06
     ass
    0.06
    늡
    0.06
    广泛的
    0.06
     wewnętrzn
    0.06
    Activations Density 0.026%

    No Known Activations