© 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. 30387
    Prev
    Next
    INDEX
    Explanations

    pill

    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
    uffy
    -0.27
    æŁ¥
    -0.27
    oby
    -0.26
    ats
    -0.26
    obe
    -0.26
     Hur
    -0.26
    oods
    -0.26
    ¦Ĥ
    -0.26
    Ỽ
    -0.25
    ä¿Ŀ
    -0.24
    POSITIVE LOGITS
    ichel
    0.31
     Stellar
    0.30
     subrange
    0.27
    .getClassName
    0.26
    -INF
    0.24
    åĤį
    0.24
    å¼¹
    0.24
    ãģ¯ä½ķ
    0.24
    	inst
    0.23
    OptionsMenu
    0.23
    Activations Density 0.438%

    No Known Activations