© 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. 21933
    Prev
    Next
    INDEX
    Explanations

    areas

    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
     Guarantee
    -0.27
    Crud
    -0.25
     Choices
    -0.25
    çĽ²
    -0.25
    æīĵæ³ķ
    -0.24
    ething
    -0.24
     constitution
    -0.24
    ño
    -0.23
     sleeper
    -0.23
    _STAT
    -0.23
    POSITIVE LOGITS
     occupational
    0.29
    ISK
    0.28
    è¡Įä¸ļåįıä¼ļ
    0.27
    UNE
    0.26
     except
    0.25
    éĶħ
    0.25
     Occupational
    0.25
    UNC
    0.24
     contracting
    0.24
    hop
    0.24
    Activations Density 0.000%

    No Known Activations