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. 130740
    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
    .extend
    -0.07
    routing
    -0.07
     Strange
    -0.07
    孽
    -0.07
    .documents
    -0.07
    写字楼
    -0.07
    سوء
    -0.07
    lang
    -0.06
    conti
    -0.06
     Var
    -0.06
    POSITIVE LOGITS
    している
    0.07
    /"↵
    0.07
    ()\
    0.07
    たら
    0.07
    :&
    0.07
    具体情况
    0.07
    :</
    0.07
    "`↵
    0.07
    prepared
    0.07
     positioned
    0.06
    Activations Density 0.001%

    No Known Activations