© 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. 22268
    Prev
    Next
    INDEX
    Explanations

    Technology and internet forums

    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
    纵横
    -0.26
    éĶ£
    -0.26
    æĹłç¼Ŀ
    -0.26
     Scha
    -0.25
     falsehood
    -0.25
    éģĦ
    -0.25
     -$
    -0.24
    ·¨
    -0.24
    交åıī
    -0.24
     administration
    -0.24
    POSITIVE LOGITS
    yny
    0.26
    amental
    0.26
    andon
    0.25
    åģļçļĦ
    0.25
    _feature
    0.24
    als
    0.24
    Features
    0.24
    æµģç¨ĭ
    0.23
    èĽ®
    0.23
    facts
    0.23
    Activations Density 0.000%

    No Known Activations