© 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. 22478
    Prev
    Next
    INDEX
    Explanations

    month-old

    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
    tin
    -0.07
    æĿ¾é¼ł
    -0.07
    ÈĽiuni
    -0.06
    bool
    -0.06
    ient
    -0.06
    åĩºåħ¶
    -0.06
    ä¸įçŁ¥éģĵèĩªå·±
    -0.06
     Batal
    -0.06
    alize
    -0.06
    frog
    -0.06
    POSITIVE LOGITS
    <|box_end|>
    0.08
    akov
    0.07
    ró
    0.07
     پاÛĮ
    0.07
     matt
    0.07
    @js
    0.07
    ุà¸ģ
    0.07
    微信æī«ä¸Ģæī«
    0.07
     determin
    0.06
     scop
    0.06
    Activations Density 0.002%

    No Known Activations