© 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. 30-TRANSCODER-HP
    7. 96858
    Prev
    Next
    INDEX
    Explanations

    licensing and copyright

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bean
    -0.32
     attitudes
    -0.28
    itudes
    -0.27
    enus
    -0.27
     cling
    -0.27
    oric
    -0.26
    omain
    -0.26
    Bean
    -0.26
    beans
    -0.26
    强迫
    -0.25
    POSITIVE LOGITS
    å¸Ī
    0.29
    mith
    0.28
    uman
    0.27
    å½ĵä¹ĭ
    0.26
    vron
    0.26
    tesy
    0.26
     CLOCK
    0.26
    ä¸ŃåĽ½äººæ°ij
    0.25
    mr
    0.25
    æ¯į
    0.25
    Activations Density 0.784%

    No Known Activations