© 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. 22067
    Prev
    Next
    INDEX
    Explanations

    technical texts

    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
    èĥ½åĬĽå¼º
    -0.28
     esk
    -0.27
     contrario
    -0.26
    å·¢
    -0.26
    å½¢åĬ¿
    -0.26
     torn
    -0.25
    errupted
    -0.24
    ñas
    -0.24
    idges
    -0.24
    æ¹ĥ
    -0.24
    POSITIVE LOGITS
    ImageContext
    0.26
    (vars
    0.24
    Explicit
    0.24
     Conscious
    0.24
    ste
    0.24
    è¿ĺæľīå¾Īå¤ļ
    0.24
    ($)
    0.24
    styled
    0.24
    bian
    0.23
     %#
    0.23
    Activations Density 0.000%

    No Known Activations