© 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. 41078
    Prev
    Next
    INDEX
    Explanations

    all

    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
    åľ¨ä¸Ĭæµ·
    -0.28
    ilon
    -0.27
    masked
    -0.27
     threading
    -0.26
    atoire
    -0.25
     starving
    -0.24
    uur
    -0.24
    éªĩ
    -0.24
    è¿ĺ羣
    -0.24
    ç¼
    -0.23
    POSITIVE LOGITS
    .opensource
    0.29
     cling
    0.29
    æĶ¿
    0.29
    она
    0.28
    ç¥ĸåĽ½
    0.25
    r
    0.24
    RU
    0.24
    æŃ£
    0.24
    建设
    0.24
    æ´ģçĻ½
    0.24
    Activations Density 0.189%

    No Known Activations