© 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. 56776
    Prev
    Next
    INDEX
    Explanations

    digestive terms

    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
    hood
    -0.10
    次çļĦ
    -0.10
    她表示
    -0.08
    cker
    -0.07
    éľīç´ł
    -0.07
    طا
    -0.07
    holders
    -0.07
    zzo
    -0.07
    quam
    -0.07
     godz
    -0.07
    POSITIVE LOGITS
    ible
    0.10
    ibility
    0.09
    al
    0.08
     xuôi
    0.08
    ä½Ĩä¸įéĻIJäºİ
    0.08
    eldorf
    0.08
    Ùĩب
    0.08
    iples
    0.08
    icult
    0.07
    æ®Ĩå°½
    0.07
    Activations Density 0.012%

    No Known Activations