© 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. 37971
    Prev
    Next
    INDEX
    Explanations

    using or construction

    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
    mok
    -0.07
    åįĥç§ĭ
    -0.06
    æľī天
    -0.06
    1
    -0.06
    濯
    -0.06
    _attention
    -0.06
    verz
    -0.06
    大å®Ĺ
    -0.05
    å¿«é¤IJ
    -0.05
    veli
    -0.05
    POSITIVE LOGITS
    icismo
    0.08
    tings
    0.08
    ertest
    0.08
    erman
    0.08
    ׼×ķ
    0.08
    å·²ä¹ħçļĦ
    0.08
    airo
    0.08
     buurt
    0.08
    spb
    0.07
    ä¸įäºĨçļĦ
    0.07
    Activations Density 0.621%

    No Known Activations