© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 32995
    Prev
    Next
    INDEX
    Explanations

    O's, hyphenated words, specific tokens

    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
    çĭŀ
    -0.09
    æ±¹
    -0.08
    igned
    -0.08
    vail
    -0.08
    èĮģ
    -0.08
    åĮĨ
    -0.08
    xada
    -0.08
    ÑĬÑĤ
    -0.08
    ä¹ĭåīij
    -0.08
    æ¶ħ
    -0.08
    POSITIVE LOGITS
    èĹıåľ¨
    0.08
    åĽłä¸ºæĺ¯
    0.08
    èĹı
    0.08
     hidden
    0.07
    å¯Ĩ
    0.07
    åĽłä¸ºæľī
    0.07
    çīĩ
    0.07
    对æĸ¹çļĦ
    0.07
     past
    0.06
    è¿ĩåİ»
    0.06
    Activations Density 0.002%

    No Known Activations