© 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. 40401
    Prev
    Next
    INDEX
    Explanations

    ial

    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
    è¶Ĭå¤ļ
    -0.30
     bow
    -0.26
    anco
    -0.25
    è¶Ĭ大
    -0.24
    æłĩåĩĨåĮĸ
    -0.23
    åłĨ积
    -0.23
    äºĨ解åĪ°
    -0.23
     District
    -0.23
    ä¿ĿæĮģçĿĢ
    -0.23
     probe
    -0.23
    POSITIVE LOGITS
    loud
    0.28
    ç¼¢
    0.27
    ians
    0.26
    ufficient
    0.26
    kok
    0.26
    zych
    0.26
    æĿ¡è¯Ħ论
    0.24
    éĻĭ
    0.23
    èĭ±éĽĦ
    0.23
    æĽĻ
    0.23
    Activations Density 0.954%

    No Known Activations