© 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. 108058
    Prev
    Next
    INDEX
    Explanations

    Numbers

    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
    .nih
    -0.26
    ä¹Ĺ
    -0.26
    dre
    -0.26
    ucher
    -0.26
     unchanged
    -0.25
    ä¹ĺ
    -0.25
    åĴĦ
    -0.24
    çļĦæķ´ä½ĵ
    -0.24
    ionale
    -0.23
    éĤª
    -0.23
    POSITIVE LOGITS
    åĢ¾æĸľ
    0.26
    vard
    0.25
    Som
    0.25
    çĺ©
    0.24
    æķĪåĬĽ
    0.24
    åķ¬
    0.23
    ylon
    0.23
     sometime
    0.23
    ersed
    0.23
    enis
    0.23
    Activations Density 2.663%

    No Known Activations