© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 41065
    Prev
    Next
    INDEX
    Explanations

    tarot, runes, astrology, oracle, interpretation

    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
    orts
    -0.08
    èĤ¥å¤§
    -0.08
    æīģæ¡ĥ
    -0.08
    è¡ĢæµĨ
    -0.07
    è®´
    -0.07
    èĽĨ
    -0.07
    æłĩé«ĺ
    -0.07
    ented
    -0.07
    į°
    -0.07
    *sizeof
    -0.07
    POSITIVE LOGITS
    åį¦
    0.10
    åIJīåĩ¶
    0.09
    äºĶè¡Į
    0.08
    æĺĵç»ı
    0.08
    interpret
    0.08
    åħ«åį¦
    0.08
    解读
    0.08
    åij¨æĺĵ
    0.08
    åįłåįľ
    0.07
     interpretation
    0.07
    Activations Density 0.006%

    No Known Activations