© 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. 12-TRANSCODER-HP
    7. 23149
    Prev
    Next
    INDEX
    Explanations

    path

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dynam
    -0.27
    sit
    -0.26
    incer
    -0.25
    rames
    -0.25
    å®ļåIJij
    -0.25
     rake
    -0.25
     dyn
    -0.24
     Dynam
    -0.24
    á¿·
    -0.24
     course
    -0.24
    POSITIVE LOGITS
    æĿ¡è¯Ħ论
    0.29
     dÆ°
    0.27
    asper
    0.25
    å®ģ
    0.25
     commission
    0.24
    æ´µ
    0.24
    ä»Ĭ天å°ıç¼ĸ
    0.24
    寧
    0.23
    質
    0.23
     Scores
    0.23
    Activations Density 0.001%

    No Known Activations