© 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. 33578
    Prev
    Next
    INDEX
    Explanations

    asking about prior history

    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
     Ско
    -0.08
     tame
    -0.08
    -dismiss
    -0.07
    åľ¨çº¿åĴ¨è¯¢
    -0.07
    umn
    -0.07
    ä¼ģä¸ļ认è¯ģ
    -0.07
    ×ķתר
    -0.07
    大æī¹
    -0.07
    ä¼ĺç§ĢæķĻå¸Ī
    -0.07
    çĻ½éª¨
    -0.07
    POSITIVE LOGITS
    å¡«åĨĻ
    0.09
     volunteered
    0.09
     hobbies
    0.09
    çĪ±å¥½
    0.09
     preferences
    0.09
     interview
    0.09
    æĹ¢å¾Ģ
    0.08
    询éĹ®
    0.08
     lifestyle
    0.08
    åŁºæľ¬ä¿¡æģ¯
    0.08
    Activations Density 0.263%

    No Known Activations