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. 2897
    Prev
    Next
    INDEX
    Explanations

    say

    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
     environments
    -0.08
     dragons
    -0.08
     Richards
    -0.07
    {})
    -0.07
    _AMOUNT
    -0.07
     Madame
    -0.07
     horses
    -0.07
     acne
    -0.07
    'class
    -0.07
    aut
    -0.07
    POSITIVE LOGITS
    克思主义
    0.07
    䔀
    0.07
    实际控制
    0.07
    cmpeq
    0.07
    サイ
    0.06
     üy
    0.06
     uncomment
    0.06
    .userService
    0.06
    狐月山
    0.06
     Киев
    0.06
    Activations Density 0.013%

    No Known Activations