© 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. 38627
    Prev
    Next
    INDEX
    Explanations

    non-English characters or complex symbols

    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
    istinguish
    -0.08
    éĵ®
    -0.08
    athers
    -0.07
    witch
    -0.07
    alach
    -0.07
     McCarthy
    -0.07
    aggio
    -0.07
    aily
    -0.07
    Ç
    -0.07
    _predicate
    -0.07
    POSITIVE LOGITS
    asan
    0.07
    éģĵ
    0.07
    ROUND
    0.07
    ç¹ģ
    0.07
    åºĶå½ĵæĮīçħ§
    0.07
    _ROUND
    0.07
     Round
    0.06
    æŃ£ç¾©
    0.06
    æ®Ĭ
    0.06
    ä»»ä½ķä¸Ģæĸ¹
    0.06
    Activations Density 0.001%

    No Known Activations