© 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. 107369
    Prev
    Next
    INDEX
    Explanations

    Mixed and varied short texts

    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
     guest
    -0.27
    à¹īà¸Ńà¸Ļ
    -0.25
    ĮĢ
    -0.25
     highest
    -0.24
     gens
    -0.24
    å¦Ĥæľīä¾µæĿĥ
    -0.24
    è¯ŀ
    -0.24
     fore
    -0.24
    eval
    -0.23
    称
    -0.23
    POSITIVE LOGITS
    anders
    0.31
    langs
    0.27
    бÑĢи
    0.26
    äd
    0.25
    è¿ĺèĥ½
    0.25
    kah
    0.25
    izons
    0.24
    æĶ¯
    0.24
    etu
    0.24
     Exposure
    0.24
    Activations Density 64.070%

    No Known Activations