© 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. 57754
    Prev
    Next
    INDEX
    Explanations

    the

    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
    主人åħ¬
    -0.27
     outright
    -0.25
    idge
    -0.25
    é¡¹çĽ®å»ºè®¾
    -0.24
    èĢħ
    -0.24
     setters
    -0.24
    imore
    -0.24
     Garc
    -0.23
    æĦĪ
    -0.23
    ierce
    -0.23
    POSITIVE LOGITS
    ä¸įå®Į
    0.27
    urf
    0.27
     politic
    0.27
    ird
    0.25
     Loves
    0.25
     responsibilities
    0.25
    ä¼łéĹ»
    0.25
    uliar
    0.24
     mish
    0.24
     spread
    0.24
    Activations Density 0.002%

    No Known Activations