© 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. 142068
    Prev
    Next
    INDEX
    Explanations

    instructions/suggestions

    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
    éĶ¯
    -0.28
    祥
    -0.28
    éĢļè¿ĩ对
    -0.26
     Gone
    -0.26
    çİ°åľ¨çļĦ
    -0.25
     Wax
    -0.25
    æĭīåĬ¨
    -0.25
    ãĥĩãĥ³
    -0.24
    æīĢè°ĵ
    -0.24
    è¿Ļç§į
    -0.24
    POSITIVE LOGITS
    atham
    0.29
    çĺ°
    0.27
     vice
    0.26
    vince
    0.25
    ıy
    0.25
    oro
    0.25
     caliber
    0.25
     vacancies
    0.24
     voters
    0.24
     Seam
    0.24
    Activations Density 15.827%

    No Known Activations