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. 88101
    Prev
    Next
    INDEX
    Explanations

    {

    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
    (def
    -0.07
     Schüler
    -0.06
    ;/
    -0.06
    "While
    -0.06
    .borderWidth
    -0.06
    受灾
    -0.06
    .lua
    -0.06
    Strike
    -0.06
    女子
    -0.06
     seria
    -0.06
    POSITIVE LOGITS
    AUTO
    0.07
    总数
    0.07
    重金属
    0.06
    acs
    0.06
    .imwrite
    0.06
    保密
    0.06
    넴
    0.06
    нести
    0.06
    วก
    0.06
    从根本上
    0.06
    Activations Density 0.022%

    No Known Activations