© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 56214
    Prev
    Next
    INDEX
    Explanations

    comment syntax and symbols

    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
    Dettagli
    -0.08
    NESS
    -0.08
    à·IJ
    -0.07
    ness
    -0.06
    vors
    -0.06
    oms
    -0.06
    esu
    -0.06
    ierer
    -0.06
    à±
    -0.06
     (_)
    -0.06
    POSITIVE LOGITS
    ìłģìĿ¸
    0.09
    ï¸ı
    0.08
    ably
    0.08
    äºĭåįĬåĬŁåĢį
    0.08
    atic
    0.08
    çĦ¶å¤§
    0.07
    ä½Ĩä¸įéĻIJäºİ
    0.07
    arine
    0.07
    ital
    0.07
    bish
    0.07
    Activations Density 0.302%

    No Known Activations