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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 130718
    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
     Math
    -0.08
     coastal
    -0.07
    مجتمع
    -0.07
     zk
    -0.07
    VR
    -0.07
    DAO
    -0.07
     metaphor
    -0.07
     Gold
    -0.07
     breastfeeding
    -0.07
    ochond
    -0.07
    POSITIVE LOGITS
    ine
    0.07
    .serial
    0.06
    ("")
    0.06
    完全没有
    0.06
     tụ
    0.06
    都没有
    0.06
     Enumerable
    0.06
    覺得
    0.06
     Grave
    0.06
    '].
    0.06
    Activations Density 0.074%

    No Known Activations