© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 24-TRANSCODER-HP
    7. 151210
    Prev
    Next
    INDEX
    Explanations

    Names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ÑģÑĤеÑĢ
    -0.28
    gies
    -0.26
    BITS
    -0.24
     _č↵
    -0.23
    erland
    -0.23
    _KHR
    -0.23
    обÑĭ
    -0.23
     `_
    -0.23
    วร
    -0.22
    ТÐIJ
    -0.22
    POSITIVE LOGITS
    ?’
    0.28
    ?”
    0.25
    elu
    0.23
    MOST
    0.23
    第ä¸ĢæĿ¡
    0.23
    _modules
    0.22
    .inter
    0.22
    eb
    0.22
    SB
    0.22
    ï¼Ł”
    0.21
    Activations Density 0.914%

    No Known Activations