© 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. 8293
    Prev
    Next
    INDEX
    Explanations

    quoted text or specific phrases

    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
    ãĢĸ
    -0.07
    æĢ§çļ®çĤİ
    -0.07
    ारà¥įà¤Ł
    -0.07
    iaan
    -0.07
    “The
    -0.07
    "You
    -0.07
    "All
    -0.06
    ainter
    -0.06
    “We
    -0.06
     Bref
    -0.06
    POSITIVE LOGITS
    俱ä¹IJéĥ¨
    0.14
    身临åħ¶å¢ĥ
    0.13
    äºĭåįĬåĬŁåĢį
    0.13
    *”
    0.13
    èĢ³çĨŁèĥ½è¯¦
    0.13
    æĸ°åĬłåĿ¡
    0.12
    åĬłæĭ¿å¤§
    0.12
    ()"
    0.12
    æ¯Ľæ³½ä¸ľ
    0.12
    两åѦä¸Ģåģļ
    0.11
    Activations Density 0.570%

    No Known Activations