© 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. 29857
    Prev
    Next
    INDEX
    Explanations

    goodman

    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
    æĸĩåĮĸ交æµģ
    -0.31
     Mixed
    -0.26
    éļĪ
    -0.26
    hos
    -0.26
    adamente
    -0.26
    涵
    -0.25
    çĭ¬ç«ĭ
    -0.25
    帮ä»ĸ
    -0.24
    udu
    -0.24
    tn
    -0.24
    POSITIVE LOGITS
    ÑĢеÑģÑĤ
    0.26
    ä½ļ
    0.25
    Enumerable
    0.25
     gắn
    0.25
    âĢĸ
    0.24
    åĽ½éģĵ
    0.24
    èģĶéĢļ
    0.24
    _fold
    0.24
    è´¯éĢļ
    0.23
    usher
    0.23
    Activations Density 2.113%

    No Known Activations