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. 129451
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    擦
    -0.07
    㸌
    -0.07
    evaluation
    -0.07
     neurological
    -0.07
    .NORTH
    -0.07
    Five
    -0.07
     Abort
    -0.07
    陀
    -0.07
    前一天
    -0.07
    日前
    -0.07
    POSITIVE LOGITS
     адрес
    0.07
    㭕
    0.07
     hiding
    0.07
    宣传片
    0.07
    )":
    0.07
    десь
    0.06
    !("{}",
    0.06
    国有企业
    0.06
     abrir
    0.06
    זן
    0.06
    Activations Density 0.016%

    No Known Activations