© 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. 29603
    Prev
    Next
    INDEX
    Explanations

    USB

    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
    æľ¯
    -0.31
    elman
    -0.29
    odom
    -0.28
    circ
    -0.28
    åĨ·æ¼ł
    -0.27
    dez
    -0.27
    stral
    -0.27
    hest
    -0.27
    bate
    -0.26
    æĬ½è±¡
    -0.25
    POSITIVE LOGITS
    èĴĻ
    0.29
    _FORMAT
    0.25
    æłİ
    0.25
    recommend
    0.25
    -ag
    0.25
    åIJīåĪ©
    0.24
    çļĦæľīæķĪ
    0.24
    æ°´æĻ¶
    0.24
     presidency
    0.24
    works
    0.24
    Activations Density 2.007%

    No Known Activations