© 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. 32603
    Prev
    Next
    INDEX
    Explanations

    repeated stimulation or use

    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
    ä¹ĭ忧
    -0.09
     adelant
    -0.08
    lea
    -0.08
    ippe
    -0.08
    erca
    -0.08
    vern
    -0.08
    leist
    -0.08
    æĺ¥æ±Ł
    -0.08
    åįķä½įåıĤåĬł
    -0.08
     siap
    -0.08
    POSITIVE LOGITS
    ä¹ħèĢĮä¹ħä¹ĭ
    0.16
    æĹ¥ä¹ħ
    0.12
     gradually
    0.12
     repeatedly
    0.11
     exposure
    0.11
    éĢIJæ¸IJ
    0.11
    æ¸IJæ¸IJåľ°
    0.11
    ä¼ļéĢIJæ¸IJ
    0.11
    累积
    0.11
    peated
    0.11
    Activations Density 0.303%

    No Known Activations