© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 9-TRANSCODER-HP
    7. 29333
    Prev
    Next
    INDEX
    Explanations

    Fluoride

    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
    Negative Logits
    éĩįè¿Ķ
    -0.26
    åħ³æĢĢ
    -0.26
    STYPE
    -0.25
    acyj
    -0.24
    è´µ
    -0.24
    /sdk
    -0.24
    Ark
    -0.24
     Falk
    -0.24
    BuilderFactory
    -0.24
    è·ĥ
    -0.24
    POSITIVE LOGITS
    assa
    0.27
     Zum
    0.25
     payable
    0.25
    衾
    0.25
    è®©ä½ł
    0.25
    åĢĴåľ¨
    0.24
     bracket
    0.24
    nier
    0.24
    ä¸įåıĬ
    0.24
    åĵĤ
    0.24
    Activations Density 0.867%

    No Known Activations