© 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. 107594
    Prev
    Next
    INDEX
    Explanations

    actually

    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
    ddie
    -0.26
    éº»æľ¨
    -0.25
    æĦıè¯Ĩ
    -0.25
    íĤ¥
    -0.24
    çļĦåħ·ä½ĵ
    -0.24
    iego
    -0.24
    èĥ½å¤Łè®©
    -0.24
     az
    -0.23
    ixe
    -0.23
    è¯ļ
    -0.23
    POSITIVE LOGITS
    리
    0.27
     Womens
    0.27
    (reverse
    0.26
    浯
    0.25
    (using
    0.25
    éĹº
    0.25
    ansk
    0.25
     reverse
    0.25
    리를
    0.24
     Nil
    0.23
    Activations Density 3.226%

    No Known Activations