© 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. 29483
    Prev
    Next
    INDEX
    Explanations

    observations and comparisons

    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
     nowadays
    -0.08
    quisite
    -0.07
    quisites
    -0.07
    bidden
    -0.07
    åıªè¦ģèĥ½
    -0.07
    ä¿Ŀè¯ģåħ¶
    -0.07
     guaranteed
    -0.07
    å¸ĤéĿ¢ä¸Ĭ
    -0.07
    alog
    -0.06
     destined
    -0.06
    POSITIVE LOGITS
     trends
    0.12
     comparisons
    0.12
     comparison
    0.11
     Overall
    0.11
    è¿ĻäºĽæķ°æį®
    0.11
     overall
    0.11
    Overall
    0.11
     comparing
    0.11
    æ¯Ķè¾ĥ
    0.11
     memcmp
    0.10
    Activations Density 0.085%

    No Known Activations