© 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. 34068
    Prev
    Next
    INDEX
    Explanations

    weeks or cases

    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
    çĿĢæīĭ
    -0.07
    али
    -0.07
    :eq
    -0.07
    çī¹åĪ«æĺ¯
    -0.07
    _MODULES
    -0.07
    é¢Ħå¤ĩ
    -0.06
     Kav
    -0.06
    istra
    -0.06
    èĭĩ
    -0.06
     Marine
    -0.06
    POSITIVE LOGITS
    ogn
    0.09
    ä¸įåĢ¦
    0.08
    æľī人认为
    0.08
    åĬłæĭ¿å¤§
    0.08
    åĨįè¿ĩ
    0.07
    礴
    0.07
    uku
    0.07
    è¿Ļæł·çļĦè¯Ŀ
    0.07
     onward
    0.07
    à¹Ħมà¹Īà¸Ńย
    0.07
    Activations Density 0.039%

    No Known Activations