© 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. 151449
    Prev
    Next
    INDEX
    Explanations

    accepted practices/formulas

    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
    ä¸ŃåIJ«æľī
    -0.28
    ä¸į代表
    -0.28
     nao
    -0.27
    ç§ĭ
    -0.25
    çļĦæīĭ
    -0.25
    peration
    -0.24
    åĵį
    -0.24
    没æľī
    -0.24
    andler
    -0.24
     Dup
    -0.24
    POSITIVE LOGITS
     universal
    0.29
    맹
    0.27
    ária
    0.27
    accur
    0.26
    amac
    0.25
    fcc
    0.25
    eden
    0.25
     accurate
    0.25
    bable
    0.25
    UNE
    0.25
    Activations Density 0.203%

    No Known Activations