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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 36293
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    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
    -W
    -0.07
     "":↵
    -0.07
     Reset
    -0.07
    资助
    -0.07
    开学
    -0.06
    ursor
    -0.06
    isk
    -0.06
    家の
    -0.06
    عارض
    -0.06
    邮寄
    -0.06
    POSITIVE LOGITS
    contr
    0.07
     erotisch
    0.07
     reprodu
    0.07
     içeris
    0.07
     attacker
    0.06
     сервер
    0.06
     complexity
    0.06
    .Common
    0.06
     Erd
    0.06
    _RANDOM
    0.06
    Activations Density 0.006%

    No Known Activations