© 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. 63844
    Prev
    Next
    INDEX
    Explanations

    duration and time spans

    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
    ocalypse
    -0.08
    cko
    -0.08
    ep
    -0.08
    thora
    -0.07
    FFECT
    -0.07
    ãģ®ãģ§ãģĤãĤĭ
    -0.07
    ÃĹ</
    -0.07
    zes
    -0.07
    usterity
    -0.07
    earch
    -0.07
    POSITIVE LOGITS
    ä¹ħçļĦ
    0.09
    ities
    0.09
    ä¸įç»Ŀ
    0.08
     longest
    0.08
    ances
    0.08
    ä¹ĭä¹ħ
    0.08
    ä¸įè¡°
    0.08
    æĢ§åŃIJ
    0.08
    ly
    0.08
    ently
    0.08
    Activations Density 0.036%

    No Known Activations