© 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. 41109
    Prev
    Next
    INDEX
    Explanations

    Random text snippets

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ements
    -0.33
    ement
    -0.30
    enario
    -0.27
    aina
    -0.26
     пÑĢоÑģ
    -0.26
    .setOutput
    -0.26
    éĵ
    -0.25
    yk
    -0.25
    ears
    -0.25
     trans
    -0.25
    POSITIVE LOGITS
    åĩĢ
    0.27
     Automatic
    0.27
    ace
    0.27
    Automatic
    0.26
    èĩªåĬ¨
    0.26
    æĿĤ
    0.26
    atte
    0.25
    Anth
    0.25
    argin
    0.24
     Gardner
    0.24
    Activations Density 0.000%

    No Known Activations