© 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. 29963
    Prev
    Next
    INDEX
    Explanations

    Raleigh, North Carolina

    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
    åĸĥ
    -0.30
    åĪĨåĮº
    -0.29
    æ´»ä¸ĭåİ»
    -0.28
    ::-
    -0.28
    å½ĵãģ¦
    -0.26
    åħļç»ĦæĪIJåijĺ
    -0.25
    èµ°ä¸ĭåİ»
    -0.24
    å¥
    -0.24
    tracer
    -0.24
     masse
    -0.23
    POSITIVE LOGITS
    æľ½
    0.30
    ButtonModule
    0.28
    å°ıå¾®
    0.26
     <![
    0.26
    åįĥ
    0.25
    AF
    0.24
    AMI
    0.24
    .ColumnHeader
    0.24
    AFE
    0.24
    aps
    0.24
    Activations Density 4.844%

    No Known Activations