© 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. 27-TRANSCODER-HP
    7. 8286
    Prev
    Next
    INDEX
    Explanations

    Un

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å¾Īæ¸ħæ¥ļ
    -0.31
    essim
    -0.29
    çļĦç¡®
    -0.28
    )arg
    -0.27
    Clearly
    -0.27
    inue
    -0.26
    piar
    -0.25
    æĹºçĽĽ
    -0.25
    ä¸įåIJĥ
    -0.25
     Clearly
    -0.24
    POSITIVE LOGITS
    gies
    0.28
    uras
    0.27
    uli
    0.25
     mailing
    0.25
    æĦ§
    0.24
    æıIJ交
    0.24
    raq
    0.24
    ãĤ³ãĥ¼ãĤ¹
    0.24
    ķĮ
    0.24
    æĽ¾ç»ı
    0.24
    Activations Density 0.005%

    No Known Activations