© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 130485
    Prev
    Next
    INDEX
    Explanations

    end of sentence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     finish
    -0.40
     finished
    -0.34
     finishes
    -0.32
    å®ĮäºĨ
    -0.31
    _finish
    -0.31
    å®Į
    -0.30
    _FINISH
    -0.29
    ä¹ĭåIJİ
    -0.29
     Finish
    -0.29
     finishing
    -0.29
    POSITIVE LOGITS
    ä¼ļå±ķ
    0.28
    ä¸įæĺ¯ä¸Ģ个
    0.24
    roof
    0.24
    inde
    0.23
    åı¯æĥ³
    0.23
     Infant
    0.23
     naï
    0.23
    comes
    0.23
    æ°ijèĪª
    0.23
    ibel
    0.23
    Activations Density 10.637%

    No Known Activations