© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 20735
    Prev
    Next
    INDEX
    Explanations

    setting a pointer

    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
    åijµ
    -0.08
    INUX
    -0.08
    ä¼ĹæīĢåij¨çŁ¥
    -0.08
    æĹłæ³ķæŃ£å¸¸
    -0.08
     reportedly
    -0.08
    _secure
    -0.08
    ÙĪÙĬØ©
    -0.08
    į¼
    -0.08
    udent
    -0.07
    ancellationToken
    -0.07
    POSITIVE LOGITS
    å½ĵä½ł
    0.08
    æŃ£åĽłä¸º
    0.07
    talk
    0.07
    ãģłãģĭãĤīãģĵãģĿ
    0.07
    éĤ£æĺ¯åĽłä¸º
    0.07
    åĽłä¸ºæľīäºĨ
    0.07
    èĪĴæľį
    0.06
     tell
    0.06
     telling
    0.06
    åıªèĥ½è¯´
    0.06
    Activations Density 0.012%

    No Known Activations