© 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. 61640
    Prev
    Next
    INDEX
    Explanations

    numbers, integer, complexity, resolution

    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
    isin
    -0.07
    åıĸæł·
    -0.07
    ahoo
    -0.07
    controls
    -0.07
     Readonly
    -0.06
    Cos
    -0.06
    ymas
    -0.06
    ahmen
    -0.06
    åįķèĸĦ
    -0.06
    æĬ½
    -0.06
    POSITIVE LOGITS
     combinations
    0.08
    çŁ³æĻ¯
    0.08
    gow
    0.08
    anything
    0.07
    ç»ĦåIJĪ
    0.07
    åĽłä¸ºæľīäºĨ
    0.07
     combinaison
    0.06
     Combination
    0.06
    éĿłå·¦
    0.06
     greed
    0.06
    Activations Density 0.002%

    No Known Activations