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. 129496
    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
    computer
    -0.07
    海拔
    -0.07
    �
    -0.07
     appell
    -0.07
     expressing
    -0.06
    minor
    -0.06
     ожи
    -0.06
    恽
    -0.06
     alas
    -0.06
    .getIn
    -0.06
    POSITIVE LOGITS
     editText
    0.08
     Desktop
    0.07
    皇马
    0.07
    美股
    0.07
    不错
    0.07
    ments
    0.07
     עכשיו
    0.07
     abuses
    0.07
    esus
    0.07
     trò
    0.07
    Activations Density 0.066%

    No Known Activations