© 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. 40490
    Prev
    Next
    INDEX
    Explanations

    boxes

    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
    ota
    -0.29
    guid
    -0.26
    çĽijäºĭä¼ļ
    -0.25
    åĪ°æľĢåIJİ
    -0.25
    ä¸įä¸Ģæł·çļĦ
    -0.24
    å±ŀäºİèĩªå·±
    -0.24
    sgiving
    -0.24
    ickle
    -0.23
     Font
    -0.23
    elligent
    -0.23
    POSITIVE LOGITS
     Intercept
    0.35
    å±ıèĶ½
    0.29
     obstruction
    0.29
    éģ®
    0.29
    éļĶçĿĢ
    0.28
    resher
    0.28
    ä¸ĢåľĪ
    0.28
    -cover
    0.28
    æĮ¡ä½ı
    0.28
    åİļ
    0.28
    Activations Density 0.564%

    No Known Activations