© 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. 25-TRANSCODER-HP
    7. 109347
    Prev
    Next
    INDEX
    Explanations

    Non-English / code / identifiers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    itchens
    -0.28
    azen
    -0.27
    Authors
    -0.27
    SENT
    -0.26
    Ùģض
    -0.25
    (Fl
    -0.25
    opens
    -0.25
     NSIndexPath
    -0.24
    èĤª
    -0.24
     (::
    -0.23
    POSITIVE LOGITS
    å±Ĥåĩº
    0.32
    ä¸Ģ带ä¸Ģè·¯
    0.27
    çĦī
    0.27
    emd
    0.26
     separately
    0.25
    ظÙħ
    0.25
     slice
    0.25
    elta
    0.24
    sted
    0.24
     storms
    0.24
    Activations Density 1.703%

    No Known Activations