© 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. 33-TRANSCODER-HP
    7. 52708
    Prev
    Next
    INDEX
    Explanations

    diving

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    Gener
    -0.26
    Fi
    -0.26
    åĤ¨å¤ĩ
    -0.25
    ercul
    -0.24
     Fi
    -0.24
     Gener
    -0.24
    æ¸ħéĨĴ
    -0.24
    ring
    -0.24
    (ti
    -0.24
    æİIJ
    -0.24
    POSITIVE LOGITS
    idebar
    0.27
    amble
    0.25
    社ä¼ļå®ŀè·µ
    0.25
     delegated
    0.25
     lines
    0.24
     sid
    0.24
    ä¸ĩ家
    0.24
    utilus
    0.23
     Lines
    0.23
    èĸı
    0.23
    Activations Density 0.015%

    No Known Activations