© 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. 29966
    Prev
    Next
    INDEX
    Explanations

    language

    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
    ä¿Ŀéļľ
    -0.29
    æľ¬èº«
    -0.28
    Exporter
    -0.28
     neg
    -0.28
    ä»¥ä¹łè¿ijå¹³
    -0.27
    _neg
    -0.25
     openings
    -0.25
     courses
    -0.25
    課ç¨ĭ
    -0.25
     exporter
    -0.24
    POSITIVE LOGITS
    ayah
    0.28
    SEP
    0.26
    geh
    0.26
    åħ«åŃĹ
    0.24
     Susp
    0.24
    (patch
    0.24
    æī¾åĽŀ
    0.24
     secular
    0.24
    fff
    0.24
    çŁ¥éģĵäºĨ
    0.24
    Activations Density 0.042%

    No Known Activations