© 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. 29381
    Prev
    Next
    INDEX
    Explanations

    basketball

    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
    Negative Logits
     VIA
    -0.27
     ov
    -0.27
     vard
    -0.27
    åĪ¹è½¦
    -0.27
     Trit
    -0.26
    sticks
    -0.26
     pl
    -0.26
    éĴİ
    -0.26
    æĺ¾
    -0.25
    илоÑģÑĮ
    -0.25
    POSITIVE LOGITS
    ogram
    0.28
    nod
    0.27
    EFR
    0.26
    å·¥ä¸ļåĽŃ
    0.25
    ummies
    0.25
    empor
    0.25
     squeeze
    0.25
    åī§éĻ¢
    0.24
    STM
    0.24
    æµĴ
    0.24
    Activations Density 0.560%

    No Known Activations