© 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. 19-TRANSCODER-HP
    7. 9500
    Prev
    Next
    INDEX
    Explanations

    Research papers/medical reports

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    è¶³å¤Ł
    -0.34
     enough
    -0.33
     Enough
    -0.32
    çŁŃæŶéĹ´åĨħ
    -0.30
    å¿«éĢŁ
    -0.30
    大约
    -0.30
    Enough
    -0.30
    è¾ĥ
    -0.29
    çĽ¸å¯¹è¾ĥ
    -0.29
    è¶³å¤ŁçļĦ
    -0.28
    POSITIVE LOGITS
    çıł
    0.27
     series
    0.26
    anson
    0.25
    egal
    0.25
    -series
    0.25
    (CONT
    0.24
    åĽ½æľī
    0.24
    ÙħÙĪا
    0.24
     aba
    0.23
     mist
    0.23
    Activations Density 0.019%

    No Known Activations