© 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. 24708
    Prev
    Next
    INDEX
    Explanations

    single stage, one time

    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
    à¹Ģรืà¹Īà¸Ńย
    -0.09
     persistente
    -0.09
    åīĶ
    -0.08
     diligently
    -0.08
     persist
    -0.08
     ALWAYS
    -0.08
    insip
    -0.08
     ëģĬìŀĦ
    -0.08
     incess
    -0.08
    ä¸įæĸŃå¢ŀåĬł
    -0.08
    POSITIVE LOGITS
    ä¸Ģ次æĢ§
    0.12
    åįķ次
    0.09
    /single
    0.09
    ä¸Ģ次
    0.09
    ä¸Ģä¸ĭåŃIJ
    0.09
    è·¨è¶Ĭå¼ı
    0.09
    (single
    0.09
    ä¸Ģæ°Ĺãģ«
    0.08
    å¿«éĢŁ
    0.08
    çŀ¬éĹ´
    0.08
    Activations Density 0.133%

    No Known Activations