© 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. 12-TRANSCODER-HP
    7. 24217
    Prev
    Next
    INDEX
    Explanations

    speech synthesis/recognition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    bsites
    -0.27
     vig
    -0.27
    åĢ¾
    -0.26
    ç»ı纪人
    -0.26
    edar
    -0.25
    brit
    -0.24
    =rand
    -0.24
    åł¡
    -0.24
    allon
    -0.24
    éŁ³
    -0.23
    POSITIVE LOGITS
    aben
    0.29
     Concept
    0.29
    åģľçķĻåľ¨
    0.28
    á
    0.28
    alphabet
    0.27
     Tay
    0.25
    ably
    0.25
    thumb
    0.25
    Africa
    0.24
    inkel
    0.24
    Activations Density 0.001%

    No Known Activations