© 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. 40435
    Prev
    Next
    INDEX
    Explanations

    Computer science / Technology

    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
    ç¼ĸåĪ¶
    -0.26
    ä¸įåIJĪçIJĨ
    -0.26
    plx
    -0.26
    rotch
    -0.25
    è¿ĩ
    -0.25
     preload
    -0.25
    æįķæįī
    -0.25
    Snapshot
    -0.25
    ç¿»
    -0.25
    ä»İä¸Ń
    -0.25
    POSITIVE LOGITS
     licens
    0.27
    ergy
    0.26
    och
    0.25
    æĺİ天
    0.25
    ization
    0.25
    IENT
    0.25
    åıŃ
    0.24
     masse
    0.24
     Works
    0.23
    ãĤ¤ãĥ«
    0.23
    Activations Density 1.575%

    No Known Activations