© 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. 20-TRANSCODER-HP
    7. 108032
    Prev
    Next
    INDEX
    Explanations

    and,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kill
    -0.26
    IOD
    -0.26
     canceled
    -0.25
    emachine
    -0.25
    YST
    -0.25
    iore
    -0.25
    _IO
    -0.24
     arc
    -0.24
    åĵĴ
    -0.24
    æł¼
    -0.24
    POSITIVE LOGITS
    ä¸Ģç«Ļ
    0.35
    ikit
    0.27
    enting
    0.26
    ä¸įæľį
    0.25
    åĩºåı£
    0.25
     cultures
    0.25
    -columns
    0.25
    ä¸įå®Į
    0.25
    æĹŃ
    0.25
    æĬ¥éģĵ
    0.24
    Activations Density 8.530%

    No Known Activations