© 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. 16933
    Prev
    Next
    INDEX
    Explanations

    username and password

    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
    -0.06
     (
    -0.06
    èĤĸ
    -0.06
     hell
    -0.06
     =
    -0.06
    å¿
    -0.06
    Ùī
    -0.06
    æĥ³åĪ°è¿ĻéĩĮ
    -0.05
    (
    -0.05
    Âł
    -0.05
    POSITIVE LOGITS
    oenix
    0.10
    ä¾ĽåºĶä¿¡æģ¯
    0.09
    åľ°åĿĢä½įäºİ
    0.09
    γάλ
    0.09
    Indented
    0.09
    inux
    0.08
    -scripts
    0.08
    BitFields
    0.08
    -zA
    0.08
     ménage
    0.08
    Activations Density 0.007%

    No Known Activations