© 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. 107194
    Prev
    Next
    INDEX
    Explanations

    Expressions of feeling/opinion

    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
    顶å±Ĥ
    -0.28
    ibraries
    -0.26
    å°ıäºĭ
    -0.26
    æĿĤ
    -0.25
    >Contact
    -0.25
    ä¸įåģľåľ°
    -0.25
    åºĶçĶ¨åľºæĻ¯
    -0.25
    yü
    -0.24
    conti
    -0.24
    鼶éĥ¨ä»¶
    -0.24
    POSITIVE LOGITS
     appointed
    0.27
    ÅŃ
    0.25
     coz
    0.24
    æ¯ķç«Łæĺ¯
    0.23
    adem
    0.23
     appoint
    0.23
    unbind
    0.23
     ка
    0.23
    Dat
    0.23
     cine
    0.23
    Activations Density 9.446%

    No Known Activations