Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 59739
    Prev
    Next
    INDEX
    Explanations

    frost

    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
     cannon
    -0.07
    นำ
    -0.07
    幹
    -0.07
    	len
    -0.07
    ✂
    -0.07
    ียว
    -0.07
     Eleven
    -0.06
     Samurai
    -0.06
    enan
    -0.06
     pad
    -0.06
    POSITIVE LOGITS
    _prices
    0.08
    |[
    0.08
    座谈会上
    0.07
     frost
    0.07
    ﯱ
    0.07
    fastcall
    0.07
    _hresult
    0.07
    ﯮ
    0.07
     predominantly
    0.07
    óst
    0.07
    Activations Density 0.006%

    No Known Activations