© 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. 21583
    Prev
    Next
    INDEX
    Explanations

    set in rooms or landmarks

    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
    æĹ¢ä¸į
    -0.07
    çĽ¸å¯¹èĢĮè¨Ģ
    -0.07
    etz
    -0.07
    ä¸įåĥı
    -0.07
    æĹłè®ºä»İ
    -0.06
    大ä½ĵ
    -0.06
    isson
    -0.06
    pit
    -0.06
    çĹĽåĵŃ
    -0.06
    çĮĽçĥĪ
    -0.06
    POSITIVE LOGITS
    å¾ģæľį
    0.08
     guests
    0.08
    æĸ°åŀĭåĨłçĬ¶çĹħæ¯Ĵ
    0.07
     ног
    0.07
    å¯
    0.07
    ankind
    0.07
    alise
    0.07
    æºĸ
    0.07
    IONI
    0.07
     slew
    0.07
    Activations Density 0.118%

    No Known Activations