© 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. 27433
    Prev
    Next
    INDEX
    Explanations

    mathematical or symbolic expressions

    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
    ihal
    -0.09
    antha
    -0.08
    uja
    -0.08
    esa
    -0.08
    å¤ĩçĶ¨
    -0.07
    åĨĴ
    -0.07
    å°±è¿ij
    -0.07
    syl
    -0.07
    UY
    -0.07
    ÑĢаÑī
    -0.07
    POSITIVE LOGITS
    åIJĪçIJĨå®īæİĴ
    0.09
    æŀĦéĢł
    0.09
     permissible
    0.08
    为äºĨ满足
    0.08
    çļĦå®īæİĴ
    0.08
    åı¯ä»¥æľī
    0.08
    å°½åı¯èĥ½åľ°
    0.08
    çļĦæľĢå°ı
    0.08
    è¿ĺå¿ħé¡»
    0.08
     minimized
    0.07
    Activations Density 0.017%

    No Known Activations