© 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. 18301
    Prev
    Next
    INDEX
    Explanations

    code, URL, auth, env

    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
    odon
    -0.07
    æįı
    -0.07
    bery
    -0.06
    ä½łæĥ³è¦ģ
    -0.06
     tuyá»ĥn
    -0.06
    é¡¹çĽ®ç»Ħ
    -0.06
    çļĦéĹ®åĢĻ
    -0.06
     chÄĥm
    -0.06
    çĸ¼çĪ±
    -0.06
    ByName
    -0.06
    POSITIVE LOGITS
    髦
    0.09
    required
    0.08
    æ¼Ĩ
    0.08
    转移
    0.08
    å®īè£ħå·¥ç¨ĭ
    0.07
    çģ¿
    0.07
    å¿ħé¡»åľ¨
    0.07
     install
    0.07
    -generator
    0.07
     instal
    0.07
    Activations Density 0.291%

    No Known Activations