© 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. 29203
    Prev
    Next
    INDEX
    Explanations

    found

    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
     staged
    -0.27
    edor
    -0.26
    éĤ£æł·çļĦ
    -0.26
    мел
    -0.26
    ecom
    -0.25
    _Des
    -0.25
    elor
    -0.24
    ä¹¾åĿ¤
    -0.24
     palate
    -0.24
    (des
    -0.24
    POSITIVE LOGITS
    å¾Īå¿«
    0.26
     nämlich
    0.26
     quickly
    0.26
    adata
    0.26
    å¿«éĢŁ
    0.25
    å§IJ妹
    0.25
    -double
    0.24
    official
    0.24
     cutter
    0.24
    âĸĪâĸĪ
    0.24
    Activations Density 5.299%

    No Known Activations