© 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. 23950
    Prev
    Next
    INDEX
    Explanations

    computer code

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ucing
    -0.26
    ее
    -0.25
    ű
    -0.25
    å¤ĩæ¡Ī
    -0.25
    WithPath
    -0.25
    å®°
    -0.25
     regexp
    -0.24
     INF
    -0.24
    UCE
    -0.24
     DESC
    -0.24
    POSITIVE LOGITS
    _annotation
    0.26
    ë³´
    0.26
     Theresa
    0.26
     orth
    0.25
    åĽ½ç½ij
    0.25
     Orth
    0.25
    lea
    0.25
    èģĶ社
    0.25
     Dunk
    0.24
    .Annotation
    0.24
    Activations Density 0.002%

    No Known Activations