© 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. 15439
    Prev
    Next
    INDEX
    Explanations

    find derivative or specific paths

    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
    åĨ¯
    -0.07
    yan
    -0.07
    ady
    -0.07
    hint
    -0.07
    ác
    -0.07
    _HASH
    -0.07
    ht
    -0.07
    éĢļè¿ĩè¿Ļ次
    -0.06
    eth
    -0.06
    it
    -0.06
    POSITIVE LOGITS
    ç¡®å®ŀæĺ¯
    0.08
    æĺ
    0.08
    ç¡®å®ŀ
    0.08
    確ãģĭãģ«
    0.08
     yes
    0.07
    WISE
    0.07
    Õ½
    0.07
     coquine
    0.07
    è¾°
    0.07
    確實
    0.07
    Activations Density 0.001%

    No Known Activations