© 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. 39616
    Prev
    Next
    INDEX
    Explanations

    types

    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
    æŃ¤é¡¹
    -0.27
    zes
    -0.27
     rings
    -0.24
    ä¿¡
    -0.24
    roups
    -0.24
    _false
    -0.23
    endforeach
    -0.23
     trib
    -0.23
    çļĦå°±æĺ¯
    -0.23
    gment
    -0.23
    POSITIVE LOGITS
    丼
    0.29
    oned
    0.27
    Validity
    0.26
     Reflex
    0.26
    gency
    0.26
     [/
    0.25
     reflex
    0.25
    ency
    0.25
    aded
    0.24
    pling
    0.24
    Activations Density 1.208%

    No Known Activations