© 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. 11167
    Prev
    Next
    INDEX
    Explanations

    altered states of consciousness

    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
    grim
    -0.09
    åħ¨ç³»åĪĹ
    -0.08
    å±¥
    -0.08
    æŁ¥çľĭåħ¨éĥ¨
    -0.07
    éĵģè¡Ģ
    -0.07
    çļĦåij½è¿IJ
    -0.07
     kompl
    -0.07
    ctor
    -0.07
    acionamento
    -0.07
    é£İéľľ
    -0.07
    POSITIVE LOGITS
     trance
    0.11
    å¢ĥçķĮ
    0.09
    å¢ĥåľ°
    0.09
    çļĦå¢ĥçķĮ
    0.08
    çĬ¶æĢģçļĦ
    0.08
    çĬ¶æĢģ
    0.08
    æģįæĥļ
    0.08
    ä½ĵéªĮåĴĮ
    0.08
     lasting
    0.08
    ä½ĵéªĮåĪ°
    0.08
    Activations Density 0.021%

    No Known Activations