© 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. 9-TRANSCODER-HP
    7. 29611
    Prev
    Next
    INDEX
    Explanations

    End or finality

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quee
    -0.26
     Covered
    -0.25
    ulton
    -0.25
     incompet
    -0.23
     convoy
    -0.23
    isdigit
    -0.23
    SSF
    -0.23
     tÃłi
    -0.23
    SSI
    -0.23
    icont
    -0.23
    POSITIVE LOGITS
     اÙĦعÙĨ
    0.30
    abe
    0.27
    liche
    0.26
     Dustin
    0.26
     Der
    0.25
    ç¾Ĭ
    0.25
    æĬĵ
    0.25
    лав
    0.25
    èĩ£
    0.25
     COPYING
    0.24
    Activations Density 0.799%

    No Known Activations