© 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. 13754
    Prev
    Next
    INDEX
    Explanations

    specify rules

    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
    æĪijçļĦæľĭåıĭ
    -0.08
    /of
    -0.08
     sovere
    -0.08
    ë¥
    -0.07
    æĪijæĿ¥è¯´
    -0.07
    iams
    -0.07
    ä¹ĭå®Ŀ
    -0.07
    AndPassword
    -0.07
    è¿Ļä¹Īå¤ļ人
    -0.07
    åı¦æľī
    -0.07
    POSITIVE LOGITS
    /update
    0.12
    /remove
    0.12
    /create
    0.12
    æĢ§åľ°
    0.11
    ively
    0.10
    /show
    0.10
    /manage
    0.10
    /find
    0.10
     the
    0.10
    /re
    0.10
    Activations Density 3.629%

    No Known Activations