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. 2666
    Prev
    Next
    INDEX
    Explanations

    code

    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
    现代
    -0.07
     międzynarod
    -0.07
     professionnel
    -0.07
    ignant
    -0.07
    ATIONAL
    -0.07
     людей
    -0.06
    ician
    -0.06
    ={$
    -0.06
    индивидуальн
    -0.06
    óln
    -0.06
    POSITIVE LOGITS
    推送
    0.08
    踌
    0.08
     publishes
    0.07
    솀
    0.07
    優惠
    0.07
    全部
    0.07
    .assertNull
    0.07
     Lau
    0.06
    阿
    0.06
     refrain
    0.06
    Activations Density 0.000%

    No Known Activations