© 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. 18-TRANSCODER-HP
    7. 89873
    Prev
    Next
    INDEX
    Explanations

    influenza

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pylint
    -0.26
    );$
    -0.25
    curity
    -0.25
    기ê´Ģ
    -0.24
    anship
    -0.24
    åĪºå®¢
    -0.24
    森æŀĹ
    -0.23
     ÑĢеÑĪи
    -0.23
    åŁİåİ¿
    -0.23
    ramento
    -0.23
    POSITIVE LOGITS
    ei
    0.32
    trinsic
    0.24
    \web
    0.24
    ej
    0.23
    çļĦ人
    0.23
     pours
    0.23
    ERO
    0.23
    IME
    0.23
    Å¡ÃŃ
    0.23
    (where
    0.23
    Activations Density 15.335%

    No Known Activations