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. 31166
    Prev
    Next
    INDEX
    Explanations

    distributed, is

    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
     haute
    -0.07
    落户
    -0.07
     wear
    -0.07
     alla
    -0.06
     belie
    -0.06
    遏制
    -0.06
     dette
    -0.06
    come
    -0.06
    atile
    -0.06
    맟
    -0.06
    POSITIVE LOGITS
    organizations
    0.09
    基金管理
    0.07
    urchases
    0.07
    .browser
    0.07
     Columns
    0.07
    breadcrumb
    0.07
    _REQUIRE
    0.07
    ItemType
    0.07
     musicians
    0.07
    녹
    0.07
    Activations Density 0.009%

    No Known Activations