© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 32-TRANSCODER-HP
    7. 42616
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    enses
    -0.26
    æŃ¢ãĤģ
    -0.25
    icated
    -0.25
     Unique
    -0.24
    илÑģÑı
    -0.24
    åħĥå·¦åı³
    -0.24
    rage
    -0.24
    ensed
    -0.24
    rift
    -0.23
    Critical
    -0.23
    POSITIVE LOGITS
    athering
    0.28
    coon
    0.26
    washing
    0.25
    ãĢļ
    0.25
     washing
    0.25
    eya
    0.25
    æ´Ĺ
    0.24
     satisf
    0.24
    ä¾Ľæ°´
    0.24
    ä¹Łå¥½
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.