© 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. 29918
    Prev
    Next
    INDEX
    Explanations

    teams

    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
    NE
    -0.27
    ra
    -0.27
    th
    -0.26
    Released
    -0.26
     pl
    -0.26
    So
    -0.26
    UE
    -0.25
    NG
    -0.25
    MD
    -0.25
    oust
    -0.25
    POSITIVE LOGITS
    ecast
    0.29
     Circ
    0.25
    (geometry
    0.25
     SID
    0.25
     circum
    0.24
    enheim
    0.24
     ActionTypes
    0.24
     Sacred
    0.24
    _fp
    0.24
    PRESS
    0.24
    Activations Density 2.495%

    No Known Activations