© 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. 32-TRANSCODER-HP
    7. 40818
    Prev
    Next
    INDEX
    Explanations

    HTML and "cruc"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æłİ
    -0.30
    distributed
    -0.30
    ONO
    -0.29
    ounty
    -0.29
    家éķ¿ä»¬
    -0.27
    olec
    -0.26
    din
    -0.25
     Distributed
    -0.25
    SizePolicy
    -0.25
    jis
    -0.25
    POSITIVE LOGITS
    ible
    0.31
    iver
    0.31
    ibles
    0.30
    ifer
    0.29
    let
    0.28
    ileo
    0.28
    ns
    0.28
    iverse
    0.27
    uce
    0.27
    er
    0.26
    Activations Density 0.004%

    No Known Activations