© 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. 24-TRANSCODER-HP
    7. 149265
    Prev
    Next
    INDEX
    Explanations

    Miscellaneous topics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     surrounded
    -0.28
    pest
    -0.26
    frame
    -0.26
    èħĮ
    -0.25
     anyway
    -0.25
    æŃ»
    -0.24
    éĻĦè¿ij
    -0.23
    ÑĥÑĩа
    -0.23
    ortex
    -0.23
     tah
    -0.23
    POSITIVE LOGITS
    IPH
    0.28
    å¿«æĬ¥
    0.28
    READING
    0.26
    å¤ĩæ¡Ī
    0.25
    ék
    0.25
    请æĤ¨
    0.25
    Seg
    0.25
    Reporting
    0.24
    åħļç»Ħç»ĩ
    0.24
    åij½è¿IJ
    0.24
    Activations Density 0.105%

    No Known Activations