© 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. 28948
    Prev
    Next
    INDEX
    Explanations

    answer or solution

    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
    å¾·åŁº
    -0.08
    ä¸Ģå¤ķ
    -0.08
    onso
    -0.08
    TTg
    -0.08
    æĺ¯éĿŀ常éĩįè¦ģçļĦ
    -0.08
    伸缩
    -0.07
    pje
    -0.07
    onha
    -0.07
    verages
    -0.07
     ALWAYS
    -0.07
    POSITIVE LOGITS
    åĽłä¸ºå®ĥ
    0.08
    åĽłä¸ºåıªæľī
    0.08
    æ
    0.08
    -worthy
    0.07
    æīĢåľ¨
    0.07
     because
    0.07
    åĽłä¸ºå¥¹
    0.07
     lor
    0.07
    because
    0.06
    åĽłä¸ºæĪij
    0.06
    Activations Density 0.011%

    No Known Activations