© 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. 33-TRANSCODER-HP
    7. 53886
    Prev
    Next
    INDEX
    Explanations

    Drilling holes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æ°Ķæģ¯
    -0.28
    æIJħ
    -0.27
     tast
    -0.27
    æĭ³
    -0.27
     Eastern
    -0.27
    åºŁå¼ĥçī©
    -0.25
    çļĦæ°Ķæģ¯
    -0.25
    Eastern
    -0.25
    -bre
    -0.25
    emu
    -0.24
    POSITIVE LOGITS
    áb
    0.29
    guna
    0.27
    CDATA
    0.26
    chner
    0.26
    board
    0.25
    aka
    0.24
     outlines
    0.23
    tmp
    0.23
    æĹ©æĻļ
    0.23
    plug
    0.23
    Activations Density 0.004%

    No Known Activations