© 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. 57377
    Prev
    Next
    INDEX
    Explanations

    code-related text

    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
    ikal
    -0.28
    æĻ´
    -0.27
    é¢ĺ缮
    -0.26
    à¸ŀร
    -0.26
    elsif
    -0.25
     real
    -0.25
    yme
    -0.24
    fulness
    -0.24
     journey
    -0.24
     realtime
    -0.23
    POSITIVE LOGITS
     Lives
    0.27
    vironment
    0.27
    ARGE
    0.27
    uentes
    0.26
    人æĢ§
    0.26
    workers
    0.25
    ç§ijåŃ¦å®¶
    0.25
    绣çŃ¹æİ¨è¿Ľ
    0.24
     recruits
    0.23
    ventario
    0.23
    Activations Density 0.000%

    No Known Activations