© 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. 15795
    Prev
    Next
    INDEX
    Explanations

    lineage and descendants

    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
    åįĬæĻĮ
    -0.07
    åĽ½æľį
    -0.07
    inspir
    -0.07
    ä¹ĭä½Ļ
    -0.07
    主è¦ģè´Łè´£
    -0.07
     outlined
    -0.07
    对人ä½ĵ
    -0.07
    åĨįæ·»
    -0.07
    dispatcher
    -0.07
    æ°´æĺŁ
    -0.07
    POSITIVE LOGITS
    ç¹ģæ®ĸ
    0.10
    edig
    0.10
     lineage
    0.09
     descendants
    0.09
     ÑĢазмно
    0.08
     offspring
    0.08
    ç¹ģèĤ²
    0.08
     genet
    0.08
    éģĹä¼ł
    0.08
    ä¸ĸ代
    0.08
    Activations Density 0.026%

    No Known Activations