© 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. 51004
    Prev
    Next
    INDEX
    Explanations

    except

    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
     Secund
    -0.07
    æ²ĥæĸ¯
    -0.07
    _side
    -0.07
    zata
    -0.07
    ardini
    -0.07
    idy
    -0.07
    æĺ¥æļĸ
    -0.07
    asco
    -0.07
    Dyn
    -0.07
     mid
    -0.07
    POSITIVE LOGITS
    ä¾ĭå¤ĸ
    0.20
    éĻ¤å¤ĸ
    0.19
    ãģłãģijãģ¯
    0.17
    çī¹æ®Ĭ
    0.17
    çī¹æ®ĬçļĦ
    0.16
    çī¹æ®ĬæĢ§
    0.15
     exception
    0.15
    ä¸İä¼Ĺä¸įåIJĮ
    0.15
    çī¹æ®ĬæĥħåĨµ
    0.15
    çŃīçī¹æ®Ĭ
    0.14
    Activations Density 0.332%

    No Known Activations