© 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. 24248
    Prev
    Next
    INDEX
    Explanations

    Dialog

    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
    nik
    -0.29
    æ²¹æ¼Ĩ
    -0.27
    åĨ¶
    -0.27
    ught
    -0.27
    ä¸įå½±åĵį
    -0.26
    umba
    -0.26
    太æ¹ĸ
    -0.25
    ascade
    -0.24
    æĹłæķ°æ¬¡
    -0.24
    ounced
    -0.24
    POSITIVE LOGITS
    @[
    0.27
    å¿ī
    0.27
    dot
    0.25
    arians
    0.25
    -dot
    0.25
     swallow
    0.24
    tober
    0.24
    æŃ£å¼ı
    0.24
     trous
    0.24
    _fast
    0.24
    Activations Density 0.000%

    No Known Activations