© 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. 30550
    Prev
    Next
    INDEX
    Explanations

    adequate or inadequate

    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
    鬣
    -0.09
    è¿ĺæĺ¯ä¸įéĶĻçļĦ
    -0.08
    aimer
    -0.08
    iforn
    -0.08
    ault
    -0.08
    æīįèĥ½å¤Ł
    -0.08
    æīįæľīåı¯èĥ½
    -0.08
    orme
    -0.08
    ondes
    -0.08
    è¿ĺæĺ¯éĿŀ常
    -0.08
    POSITIVE LOGITS
    o
    0.07
     anymore
    0.06
    le
    0.06
    дино
    0.06
    ARGE
    0.06
     entirely
    0.06
    ias
    0.06
     altogether
    0.06
     resolution
    0.06
    ahi
    0.06
    Activations Density 0.127%

    No Known Activations