© 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. 22-TRANSCODER-HP
    7. 112231
    Prev
    Next
    INDEX
    Explanations

    8

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .datatables
    -0.27
    tures
    -0.26
    edly
    -0.26
    atively
    -0.25
    æĭĤ
    -0.25
    lessly
    -0.24
     dodge
    -0.24
     testcase
    -0.24
    fdb
    -0.24
    碣
    -0.24
    POSITIVE LOGITS
    arn
    0.27
    ae
    0.26
    çļĦä»·åĢ¼
    0.26
    çļĦ缸åħ³
    0.25
    ä»·åĢ¼
    0.25
    ubi
    0.24
     recent
    0.24
    ota
    0.24
    ARN
    0.24
    Ľå»º
    0.24
    Activations Density 0.140%

    No Known Activations