© 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. 22282
    Prev
    Next
    INDEX
    Explanations

    confront

    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
    _residual
    -0.26
    åįģåŃĹ
    -0.25
    ignon
    -0.25
    龸
    -0.25
    lein
    -0.24
    learn
    -0.24
    ner
    -0.24
     franca
    -0.24
    =cut
    -0.24
    çļĦæ¯Ķä¾ĭ
    -0.23
    POSITIVE LOGITS
     sadd
    0.29
     carry
    0.28
     judge
    0.25
     Chatt
    0.24
     Orient
    0.24
    ť
    0.24
    Offsets
    0.24
     preview
    0.24
    dj
    0.23
     downs
    0.23
    Activations Density 0.000%

    No Known Activations