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. 109907
    Prev
    Next
    INDEX
    Explanations

    say "ography"

    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
     estimating
    -0.07
    .getResponse
    -0.07
    ilated
    -0.07
    ɛ
    -0.07
     GNU
    -0.07
    빨
    -0.07
    颁奖
    -0.07
    清爽
    -0.07
     Defensive
    -0.07
    .Maximum
    -0.07
    POSITIVE LOGITS
     الجامعة
    0.07
    崿
    0.07
    HOLDER
    0.07
    襄阳
    0.07
    쏨
    0.06
    津
    0.06
    racuse
    0.06
     Nội
    0.06
    ([[
    0.06
     khuôn
    0.06
    Activations Density 0.005%

    No Known Activations