© 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. 130677
    Prev
    Next
    INDEX
    Explanations

    Text snippets

    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
    åĴĮæľįåĬ¡
    -0.28
    çļĦå½±åĵį
    -0.27
     SPL
    -0.27
    -Headers
    -0.26
     Alta
    -0.26
     {?}
    -0.24
    den
    -0.24
    BSD
    -0.24
     influence
    -0.23
    ãģĵãģĿ
    -0.23
    POSITIVE LOGITS
     replic
    0.26
    ë°°
    0.25
    人æĢ§
    0.25
    æł·æĿ¿
    0.24
    以åIJİ
    0.24
    éļıåį³
    0.24
    FullPath
    0.24
     multin
    0.23
    ä¸ĭåİ»
    0.23
    èµ°ä¸ĭåİ»
    0.23
    Activations Density 10.771%

    No Known Activations