© 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. 14-TRANSCODER-HP
    7. 40599
    Prev
    Next
    INDEX
    Explanations

    Common prepositions and conjunctions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æı½
    -0.30
    窦
    -0.26
    缴
    -0.26
     package
    -0.25
    LBL
    -0.25
    rogate
    -0.25
    æĤ¬
    -0.24
    usu
    -0.24
    packages
    -0.24
     SUS
    -0.24
    POSITIVE LOGITS
    agem
    0.30
    æģ°å¥½
    0.26
    ANTED
    0.25
    ited
    0.24
    $fields
    0.24
    æĹĭ
    0.23
     ×ij×ĵ×Ļ×ķק
    0.23
     PIXEL
    0.23
    íĴĪ
    0.23
    wich
    0.23
    Activations Density 1.161%

    No Known Activations