© 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. 29613
    Prev
    Next
    INDEX
    Explanations

    Bracketed symbols and code

    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
    age
    -0.30
    èIJ½
    -0.29
    nage
    -0.27
    è··
    -0.26
    ardo
    -0.25
    cube
    -0.25
    临
    -0.25
     fetching
    -0.25
     She
    -0.24
     executes
    -0.23
    POSITIVE LOGITS
     Kensington
    0.32
    viol
    0.29
    è¶ħé¢Ŀ
    0.29
    鬲
    0.28
    ublic
    0.27
    åŃķæľŁ
    0.25
    ç½ijç»ľä¼łæĴŃ
    0.25
     Brigade
    0.25
    aud
    0.25
    主åĬĽåĨĽ
    0.24
    Activations Density 0.205%

    No Known Activations