© 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. 26786
    Prev
    Next
    INDEX
    Explanations

    second, more, abundant

    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
     Probably
    -0.08
    andong
    -0.08
     probably
    -0.08
    ä¸ĭè¿°
    -0.08
    ä¼ij
    -0.07
    ichtung
    -0.07
    以ä¸ĭæĿ¡ä»¶
    -0.07
    igna
    -0.07
    æĢķæĺ¯
    -0.07
    achim
    -0.07
    POSITIVE LOGITS
    صØŃ
    0.08
    åIJįåī¯åħ¶å®ŀçļĦ
    0.08
    æĢ»æ¯Ķ
    0.08
    åĩºä¹İ
    0.07
    ccb
    0.07
    åľĨ满ç»ĵæĿŁ
    0.07
    ).(
    0.07
    å¸Ĥ人æ°ijæ³ķéĻ¢
    0.07
    ืà¹īà¸Ń
    0.07
    Ł
    0.06
    Activations Density 0.026%

    No Known Activations