© 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. 40777
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    iveness
    -0.30
    IONS
    -0.29
     risen
    -0.27
    ushman
    -0.26
     Samar
    -0.26
    ional
    -0.26
    nings
    -0.25
    亲
    -0.25
    ions
    -0.25
     codes
    -0.25
    POSITIVE LOGITS
     purse
    0.29
    omid
    0.27
    typing
    0.24
    åľ¨è·¯ä¸Ĭ
    0.24
    Advertisements
    0.24
    è¿ĻæŶåĢĻ
    0.24
    ZY
    0.23
    ä¸Ģ个æĺ¯
    0.23
    æĻļä¼ļ
    0.23
    åģı
    0.23
    Activations Density 0.063%

    No Known Activations

    This feature has no known activations.