© 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. 22275
    Prev
    Next
    INDEX
    Explanations

    issues arising or issues with

    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
    spre
    -0.08
    olec
    -0.07
    cano
    -0.07
    иÑģÑĤеÑĢ
    -0.07
    orst
    -0.07
    飬
    -0.07
    ovu
    -0.07
    anship
    -0.07
    ,top
    -0.07
    ä½ľåĪĻ
    -0.07
    POSITIVE LOGITS
    åľ¨äºİ
    0.10
    ä»Ģä¹ĪéĹ®é¢ĺ
    0.10
    çļĦéĹ®é¢ĺæĺ¯
    0.09
     issues
    0.09
     khÄĥn
    0.09
     arise
    0.09
    个éĹ®é¢ĺ
    0.08
     arises
    0.08
     Issues
    0.08
     dÄĹl
    0.08
    Activations Density 0.207%

    No Known Activations