© 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. 64104
    Prev
    Next
    INDEX
    Explanations

    objective: true, existence, timeless

    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
    פ×ķר
    -0.08
    iband
    -0.08
    åħ¨èĪ¬
    -0.08
    defaults
    -0.08
    æŃ£å¸¸çļĦ
    -0.07
    )$_
    -0.07
    åĻ
    -0.07
    ç·łãĤģ
    -0.07
    LOPT
    -0.07
    Äĥn
    -0.07
    POSITIVE LOGITS
    çļĦåŃĺåľ¨
    0.09
    åŃĺåľ¨äºİ
    0.09
    çĭ¬ç«ĭ
    0.09
     transc
    0.09
     FIXED
    0.08
     existence
    0.08
     immutable
    0.08
    åŃĺåľ¨çļĦ
    0.08
    æ°¸æģĴ
    0.08
     timeless
    0.08
    Activations Density 0.021%

    No Known Activations