© 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. 130585
    Prev
    Next
    INDEX
    Explanations

    measurements

    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
    iability
    -0.32
    ngth
    -0.28
    perimental
    -0.25
    fulness
    -0.25
    unky
    -0.24
    å¹´ä¸ĬåįĬå¹´
    -0.24
    enght
    -0.24
    åķ¡
    -0.24
    roma
    -0.23
    é«Ń
    -0.23
    POSITIVE LOGITS
    gs
    0.27
     Bosch
    0.26
    æĺ¯çľŁçļĦ
    0.25
    Arrow
    0.24
    ritos
    0.24
    å¼Ĭ
    0.24
    æĢ»æľī
    0.24
     mutually
    0.23
     module
    0.23
    -modules
    0.23
    Activations Density 0.006%

    No Known Activations