© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 30-TRANSCODER-HP
    7. 95402
    Prev
    Next
    INDEX
    Explanations

    universities and colleges

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    staff
    -0.31
     local
    -0.27
    inia
    -0.27
    local
    -0.27
    -local
    -0.26
    å½ĵåľ°
    -0.26
    izia
    -0.26
    èĢĥå¯Ł
    -0.26
    -alone
    -0.26
     tag
    -0.26
    POSITIVE LOGITS
    渲æŁĵ
    0.29
     fashionable
    0.28
    actory
    0.28
    weis
    0.27
    enterprise
    0.26
    çļĦä¸Ģ款
    0.25
     conspicuous
    0.25
    å»ĵ
    0.25
    atory
    0.25
    OMIC
    0.24
    Activations Density 0.888%

    No Known Activations