© 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. 40353
    Prev
    Next
    INDEX
    Explanations

    Code/technical content

    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
    æłĭ
    -0.25
    çªĺ
    -0.25
    ç«ĭæ¡Ī
    -0.25
    çī¹å®ļ
    -0.24
    贵宾
    -0.24
    æĹ¥å¸¸
    -0.24
     Tre
    -0.24
     Vet
    -0.23
    çŃ¾ç½²
    -0.23
    éĿĻ
    -0.23
    POSITIVE LOGITS
    igu
    0.28
    icap
    0.26
    ghan
    0.26
     Loch
    0.25
    -Za
    0.25
    _adv
    0.25
    oldown
    0.24
    maal
    0.24
    ABCDEFGHIJKLMNOP
    0.24
    ÑĦик
    0.24
    Activations Density 0.017%

    No Known Activations