© 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. 41673
    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
    ãģªãģijãĤĮãģ°
    -0.26
    åĪĨæķ°
    -0.25
    å¯ĨéĽĨ
    -0.25
    .useState
    -0.24
    vers
    -0.24
    æķ´é½IJ
    -0.24
    rá
    -0.23
    éģĹ
    -0.23
    å¼¥
    -0.23
    URED
    -0.23
    POSITIVE LOGITS
    ngen
    0.27
    permit
    0.26
    elin
    0.26
    ì©Ķ
    0.25
     blew
    0.25
    udios
    0.25
    .deepcopy
    0.24
    .Generic
    0.24
    arnings
    0.24
     pissed
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.