© 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. 46776
    Prev
    Next
    INDEX
    Explanations

    to confirm feasibility

    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
    .).
    -0.07
    è¡·
    -0.07
    ”ãĢĤ
    -0.07
    erah
    -0.07
    ).
    -0.07
    ï¼Ľ
    -0.06
    ï¼īãĢĤ
    -0.06
    ;
    -0.06
    }'.
    -0.06
    eron
    -0.06
    POSITIVE LOGITS
    èµ·è§ģ
    0.15
     ìľĦíķ´ìĦľëĬĶ
    0.11
    ,it
    0.10
     ×ķ׾×Ķ
    0.10
    æĢİä¹ĪåĬŀåij¢
    0.10
    ãģĻãĤĭãģ«ãģ¯
    0.10
    íķĺ볤면
    0.10
    ,this
    0.10
     обаÑĩе
    0.09
     _______,
    0.09
    Activations Density 0.323%

    No Known Activations