© 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. 38526
    Prev
    Next
    INDEX
    Explanations

    ligands and abbreviations

    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
    eny
    -0.08
    éĻĪå¿Ĺ
    -0.08
    ekk
    -0.07
    éĻĪåħĪçĶŁ
    -0.07
    undert
    -0.07
    uari
    -0.07
    çŁ¥éģĵä½ł
    -0.07
    ØŃض
    -0.07
    iversary
    -0.07
    ettle
    -0.07
    POSITIVE LOGITS
    以ä¸ĭç®Ģ称
    0.08
    åĬłæĭ¿å¤§
    0.07
    impse
    0.07
    åĪ©æĸ¯
    0.07
    ftware
    0.07
    ialect
    0.06
     abbreviated
    0.06
    ÙĬÙĦØ©
    0.06
    icense
    0.06
    æ²½
    0.06
    Activations Density 0.021%

    No Known Activations