© 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. 42047
    Prev
    Next
    INDEX
    Explanations

    Nevertheless, and similar conjunctions

    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
     zwar
    -0.08
     addirittura
    -0.08
    æł¹æľ¬æ²¡æľī
    -0.08
    èĻ½å°ı
    -0.08
     вообÑīе
    -0.07
     ÑģооÑĤвеÑĤÑģÑĤвенно
    -0.07
    ä¿ij
    -0.07
    stra
    -0.07
    ³
    -0.07
    ç®Ģ缴
    -0.07
    POSITIVE LOGITS
     ë¶Ī구íķĺê³ł
    0.11
    forth
    0.09
    æ»ĵ
    0.08
    éĩįè¦ģçļĦæĺ¯
    0.08
    Ñĭми
    0.07
    enek
    0.07
    ãģ¡ãģ«
    0.07
    ÑģÑĤав
    0.07
    িদ
    0.07
    acker
    0.07
    Activations Density 0.026%

    No Known Activations