© 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. 15942
    Prev
    Next
    INDEX
    Explanations

    the only

    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
    isty
    -0.09
    леÑĨ
    -0.08
    andatory
    -0.08
    -fw
    -0.08
    iscal
    -0.08
    Stroke
    -0.07
    ĴĪ
    -0.07
    ìľłìĿĺ
    -0.07
    æĥ³çŁ¥éģĵçļĦçŃĶæ¡Ī
    -0.07
    大å°Ĩ
    -0.07
    POSITIVE LOGITS
    èİ«è¿ĩäºİ
    0.08
     conceivable
    0.08
     way
    0.07
     possible
    0.07
    owing
    0.07
    ä¾ĭå¤ĸ
    0.06
    ling
    0.06
     feasible
    0.06
    omor
    0.06
    è¿Ļæł·æīįèĥ½
    0.06
    Activations Density 0.009%

    No Known Activations