© 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. 57211
    Prev
    Next
    INDEX
    Explanations

    <html

    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
    æľīä¸Ģå®ļ
    -0.28
    æľīåIJį
    -0.26
    ä¸Ģå®ļ
    -0.26
    æ¦Ĥ
    -0.26
     setw
    -0.25
     plais
    -0.25
    ï¿¥
    -0.25
    _probe
    -0.25
    ifik
    -0.25
     surround
    -0.25
    POSITIVE LOGITS
     cur
    0.29
    LOAT
    0.26
    cur
    0.26
    Cur
    0.25
    è¿IJ
    0.24
    oader
    0.24
    rate
    0.24
     Racing
    0.24
     hel
    0.24
     Tre
    0.24
    Activations Density 0.001%

    No Known Activations