© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7497
    Prev
    Next
    INDEX
    Explanations

    presence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Curse
    -0.30
    æŃ£å½ĵ
    -0.24
     Wind
    -0.24
    ycin
    -0.23
    é£İ
    -0.23
    èģĶ
    -0.23
     Boulevard
    -0.23
    -navigation
    -0.23
    ä¸įåĪ©
    -0.22
    ç«ŀ
    -0.22
    POSITIVE LOGITS
    ful
    0.27
    ÂŃs
    0.27
     LOC
    0.26
    /output
    0.25
    eof
    0.24
    god
    0.24
    URE
    0.24
     resultant
    0.23
    ä¸İåIJ¦
    0.23
    ologic
    0.23
    Activations Density 2.002%

    No Known Activations