© 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. 29509
    Prev
    Next
    INDEX
    Explanations

    end

    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
     CDDL
    -0.28
    ods
    -0.25
    åŃ£èĬĤ
    -0.24
     appeals
    -0.24
    æĬľ
    -0.24
    è¦ı
    -0.24
    adin
    -0.24
     approaches
    -0.23
    -out
    -0.23
    riminal
    -0.23
    POSITIVE LOGITS
    主治
    0.26
    ç©´
    0.25
     Institute
    0.25
    äºĭåĦ¿
    0.24
    lands
    0.24
     Instit
    0.23
    baugh
    0.23
     programm
    0.23
    =X
    0.23
     Eig
    0.23
    Activations Density 3.316%

    No Known Activations