© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14347
    Prev
    Next
    INDEX
    Explanations

    parentheses followed by letters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸įåįķ
    -0.07
    å¥ł
    -0.07
    à¸Ĺีà¹Īà¸ķัà¹īà¸ĩ
    -0.07
    heus
    -0.07
    cce
    -0.07
    afe
    -0.07
    çħ¦
    -0.07
    heit
    -0.07
    auge
    -0.07
    ;padding
    -0.07
    POSITIVE LOGITS
    /uploads
    0.07
    —is
    0.06
     IsValid
    0.06
    zak
    0.06
    ardin
    0.06
    à¹Īาà¸Ļ
    0.06
    æīĭãģ§
    0.06
    说æĿ¥
    0.06
    -results
    0.06
     flank
    0.06
    Activations Density 0.011%

    No Known Activations