© 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. 61246
    Prev
    Next
    INDEX
    Explanations

    vice versa

    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
    agnes
    -0.07
     há»Ļp
    -0.07
    å±±æ¹ĸ
    -0.07
    å¿«å¿«ä¹IJ
    -0.07
    åİĭåĬĽå¤§
    -0.07
    sos
    -0.06
    _DECLARE
    -0.06
    _DIP
    -0.06
     quadr
    -0.06
    DEFINE
    -0.06
    POSITIVE LOGITS
    çł
    0.08
    spot
    0.07
    å°½
    0.07
    schluss
    0.07
    åħ®
    0.06
    ä»Ģ
    0.06
    æľªå¿ħ
    0.06
    aska
    0.06
    ãģĵãģ¡ãĤīãģ¯
    0.06
    åºĬ
    0.06
    Activations Density 0.011%

    No Known Activations