© 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. 50011
    Prev
    Next
    INDEX
    Explanations

    languages and code constructs

    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
    Ñİз
    -0.08
    зино
    -0.08
    awn
    -0.07
    大åĵŃ
    -0.07
    icos
    -0.07
    Ỽc
    -0.07
    eton
    -0.07
    æľĿæ°Ķ
    -0.07
    otos
    -0.07
    ocache
    -0.06
    POSITIVE LOGITS
    åŃķ
    0.07
    æ¯ı天éĥ½ä¼ļ
    0.07
    dk
    0.07
    è¯ĨåŃĹ
    0.06
    åľ°æĬĬ
    0.06
    åľ°å®ĮæĪIJ
    0.06
    ersive
    0.06
    ิรà¹Į
    0.06
    ä¸įæĸŃæ·±åĮĸ
    0.06
    éĻį
    0.06
    Activations Density 0.061%

    No Known Activations