© 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. 9-TRANSCODER-HP
    7. 29470
    Prev
    Next
    INDEX
    Explanations

    see

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ersh
    -0.30
    ä¸įçĶ¨æĭħå¿ĥ
    -0.28
    eted
    -0.27
    å®ĮæĪIJäºĨ
    -0.26
     assist
    -0.24
    iero
    -0.24
     horns
    -0.24
     navig
    -0.23
    漫éķ¿
    -0.23
     Implemented
    -0.23
    POSITIVE LOGITS
    éĺ±
    0.29
    æ´ŀå¯Ł
    0.26
    ién
    0.26
    destruct
    0.25
     Giov
    0.24
    æļ´
    0.24
     trough
    0.24
     womb
    0.24
    inz
    0.24
    çĺ¾
    0.24
    Activations Density 2.480%

    No Known Activations