© 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. 38540
    Prev
    Next
    INDEX
    Explanations

    less or slower than

    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
    éri
    -0.07
    寨
    -0.07
    ugier
    -0.07
    祺
    -0.07
    èĩªéĢī
    -0.07
     decent
    -0.06
    éķ¿çº¦
    -0.06
    _NATIVE
    -0.06
    ukt
    -0.06
    åİ®
    -0.06
    POSITIVE LOGITS
     voire
    0.10
    ä¸ŃæŃ£
    0.08
    çĶļèĩ³
    0.08
    çĶļèĩ³ä¼ļ
    0.08
    éĴĿ
    0.08
     neutral
    0.08
    åĩıå¼±
    0.08
    çĶļèĩ³æĺ¯
    0.08
    æ¸Ľ
    0.08
    çĶļèĩ³åľ¨
    0.07
    Activations Density 0.026%

    No Known Activations