© 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. 30009
    Prev
    Next
    INDEX
    Explanations

    period

    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
    [List
    -0.30
    åĨĪ
    -0.27
     usu
    -0.27
     pickup
    -0.27
    DOC
    -0.26
     kinetic
    -0.26
    GG
    -0.25
     recover
    -0.25
    æĥħ
    -0.24
     ex
    -0.24
    POSITIVE LOGITS
    ä¸ĭæĿ¥çļĦ
    0.29
    跨度
    0.27
    ä¸įè§ģäºĨ
    0.27
    .@
    0.27
    -def
    0.26
    ä¹Ĥ
    0.26
    被åijĬ
    0.25
    (MigrationBuilder
    0.25
     Boeh
    0.25
     phé
    0.25
    Activations Density 3.188%

    No Known Activations