© 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. 43059
    Prev
    Next
    INDEX
    Explanations

    Russian administrative districts

    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
    c
    -0.07
    íĦ°
    -0.06
    miner
    -0.06
    free
    -0.06
    alp
    -0.06
    /activity
    -0.06
    תר
    -0.06
    åĴĮåĪ©çĶ¨
    -0.06
     nik
    -0.06
    lack
    -0.06
    POSITIVE LOGITS
    ÃŃm
    0.08
    apore
    0.07
    oodoo
    0.07
    å¼ºåĽ½
    0.07
    à¸ŀย
    0.07
    ickname
    0.07
    ä¸ĩå¥Ĺ
    0.07
    kada
    0.07
    çĻ¾å®¶
    0.07
    åŃķ
    0.07
    Activations Density 0.001%

    No Known Activations