© 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. 14-TRANSCODER-HP
    7. 41581
    Prev
    Next
    INDEX
    Explanations

    tumor

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     deducted
    -0.26
    otes
    -0.25
    éĽħ
    -0.25
     reconstructed
    -0.24
    âļ¡
    -0.24
    _suffix
    -0.24
    weg
    -0.24
     +/-
    -0.24
     courts
    -0.23
    ä¿®å¤į
    -0.23
    POSITIVE LOGITS
    ivable
    0.27
    袢
    0.26
    HSV
    0.25
    èĩªä¸»åĵģçīĮ
    0.25
    ä½ľæģ¯
    0.24
     consumption
    0.24
    anny
    0.24
    utron
    0.24
    _Obj
    0.24
    è§Ĵèī²
    0.24
    Activations Density 1.015%

    No Known Activations