© 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. 959
    Prev
    Next
    INDEX
    Explanations

    exceptions and but

    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
    ®
    -0.07
    ä½ĨçĶ±äºİ
    -0.07
    ĸ
    -0.07
    æľīçĤ¹
    -0.06
    èĻ½çĦ¶æ²¡æľī
    -0.06
    大åĨĻ
    -0.06
    NSE
    -0.06
    Ùģض
    -0.06
    forge
    -0.06
    adat
    -0.06
    POSITIVE LOGITS
     exceptions
    0.10
    åį³ä¾¿å¦ĤæѤ
    0.09
     looph
    0.08
     exception
    0.08
    _exceptions
    0.08
     Exceptions
    0.08
    occhi
    0.08
    agh
    0.08
    odelist
    0.08
    代价
    0.07
    Activations Density 0.075%

    No Known Activations