© 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. 14-TRANSCODER-HP
    7. 40713
    Prev
    Next
    INDEX
    Explanations

    extend

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èĤ¥
    -0.29
    æĹĮ
    -0.28
    Af
    -0.27
    æī©å±ķ
    -0.26
    å§ĭ
    -0.26
     obe
    -0.26
    æ´ª
    -0.25
     Wer
    -0.25
     ob
    -0.25
     Af
    -0.24
    POSITIVE LOGITS
    esis
    0.27
    .Evaluate
    0.26
    çļĦåķĨåĵģ
    0.25
    ioned
    0.25
    ions
    0.25
     globals
    0.24
    西äºļ
    0.24
    人åıĤ
    0.24
    inker
    0.23
    ç¼ij
    0.23
    Activations Density 2.385%

    No Known Activations