© 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. 29591
    Prev
    Next
    INDEX
    Explanations

    picture

    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
     Sing
    -0.25
    Det
    -0.25
    为èĩªå·±
    -0.25
    walls
    -0.25
    .portal
    -0.25
    ç£ķ
    -0.25
    idl
    -0.24
     song
    -0.24
     Walls
    -0.24
    æľīæĽ´å¤ļçļĦ
    -0.24
    POSITIVE LOGITS
    çĶŁåij½åij¨æľŁ
    0.26
    anto
    0.25
    设计
    0.25
     hides
    0.24
     lifes
    0.24
    çĶŁåij½
    0.24
    èĨĤ
    0.24
    rollo
    0.24
    leton
    0.24
    ROUND
    0.24
    Activations Density 1.054%

    No Known Activations