© 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. 58242
    Prev
    Next
    INDEX
    Explanations

    introduced

    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
    åıªæľīèĩªå·±
    -0.08
    -trained
    -0.08
    æĮīè¦ģæ±Ĥ
    -0.07
     usual
    -0.07
    çĶļèĢħ
    -0.07
    ä¼ļæľīä¸ĢäºĽ
    -0.07
    æ¯Ķæ¯Ķ
    -0.07
    åıijå¸ĥä¿¡æģ¯
    -0.07
    Caught
    -0.07
    åıĪåĪ°äºĨ
    -0.07
    POSITIVE LOGITS
     concepts
    0.10
     erstmals
    0.09
     ì²ĺìĿĮìľ¼ë¡ľ
    0.09
    å¥łå®ļäºĨåŁºç¡Ģ
    0.09
     unprecedented
    0.09
     damals
    0.09
    ç¡®ç«ĭäºĨ
    0.09
    åľ¨å½ĵæŶ
    0.09
     впеÑĢвÑĭе
    0.08
    åīįæīĢæľªæľīçļĦ
    0.08
    Activations Density 0.234%

    No Known Activations