© 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. 61589
    Prev
    Next
    INDEX
    Explanations

    manifestation, corruption, humility, heterogeneity, resilience, advocate, difference, tolerance

    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
    è´¸
    -0.08
    áte
    -0.08
    elte
    -0.07
    Serializable
    -0.07
    å®Ĺ
    -0.07
    æµ·é»ĺ
    -0.07
    ẩu
    -0.07
    otta
    -0.07
    زÙĬد
    -0.07
    éģĵ人
    -0.07
    POSITIVE LOGITS
    主è¦ģ表çİ°åľ¨
    0.13
    表çİ°åľ¨
    0.13
    ä½ĵçİ°åľ¨
    0.12
    主è¦ģä½ĵçİ°åľ¨
    0.12
     manifested
    0.09
    ç¨ĭ度
    0.08
    表çİ°å½¢å¼ı
    0.08
    表çݰ为
    0.08
    çľĭå¾Ĺè§ģ
    0.07
     means
    0.07
    Activations Density 0.098%

    No Known Activations