© 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. 30215
    Prev
    Next
    INDEX
    Explanations

    out

    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
    å¥Ĺè£ħ
    -0.27
    .removeChild
    -0.26
    å·¥ä½ľä½ľé£İ
    -0.26
    born
    -0.24
    agus
    -0.24
     Ivanka
    -0.24
    /bg
    -0.24
    ordinate
    -0.24
     mistress
    -0.24
     intervene
    -0.24
    POSITIVE LOGITS
     all
    0.29
    inqu
    0.27
    æĹģ
    0.26
    æīĢæľī
    0.26
    phin
    0.26
    all
    0.25
    	register
    0.25
    åĺĽ
    0.25
    inem
    0.25
    æħİ
    0.24
    Activations Density 0.798%

    No Known Activations