© 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. 25-TRANSCODER-HP
    7. 106940
    Prev
    Next
    INDEX
    Explanations

    various sources

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    侯
    -0.26
     avi
    -0.26
    $field
    -0.26
    çķĻä¸ĭ
    -0.26
     Bog
    -0.25
    <quote
    -0.25
     calle
    -0.25
    ä¸į代表
    -0.24
    åĢĻ
    -0.24
    ",[
    -0.24
    POSITIVE LOGITS
    otec
    0.29
    ufs
    0.28
    PROC
    0.28
    standing
    0.26
    version
    0.26
    aclass
    0.26
    .git
    0.25
    бил
    0.24
    æĩĬ
    0.23
     opc
    0.23
    Activations Density 0.147%

    No Known Activations