© 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. 112153
    Prev
    Next
    INDEX
    Explanations

    Comparisons

    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
    olland
    -0.28
    orton
    -0.25
    ä¸įå¾Ĺ转载
    -0.24
    acet
    -0.24
     lac
    -0.24
    issing
    -0.23
    imentary
    -0.23
    entially
    -0.23
    emale
    -0.23
    quared
    -0.23
    POSITIVE LOGITS
     like
    0.72
    å°±åĥı
    0.58
     Like
    0.58
    åĥı
    0.58
    like
    0.58
     LIKE
    0.52
    å¦Ĥ
    0.52
    ä¸Ģå¦Ĥ
    0.50
    å¦ĤåIJĮ
    0.49
    Like
    0.48
    Activations Density 0.006%

    No Known Activations