© 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. 46349
    Prev
    Next
    INDEX
    Explanations

    asking questions

    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
    åѦåĪ¶
    -0.07
    çIJĨ论çłĶ究
    -0.07
    æݪ置
    -0.07
     demise
    -0.07
    WM
    -0.07
    æķĻå¸ĪéĺŁä¼į
    -0.07
    defgroup
    -0.06
    åĬĪ
    -0.06
    overall
    -0.06
    绣ä¸Ģ管çIJĨ
    -0.06
    POSITIVE LOGITS
     prompts
    0.10
     elic
    0.09
     brainstorm
    0.09
    æıIJçĤ¼
    0.09
    åľ¨è¡ĮåĬ¨
    0.09
    ç»ĵæŀĦåĮĸ
    0.08
    åĩĿ
    0.08
     interrog
    0.08
     actionable
    0.08
     consciously
    0.08
    Activations Density 0.027%

    No Known Activations