© 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. 31934
    Prev
    Next
    INDEX
    Explanations

    equivalent

    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
    anke
    -0.07
    为载ä½ĵ
    -0.07
    符åIJĪåĽ½å®¶
    -0.07
    angk
    -0.07
     choke
    -0.07
    .conf
    -0.06
    ä¹Łç¡®å®ŀ
    -0.06
    عتÙĩا
    -0.06
    éħ¬
    -0.06
    ego
    -0.06
    POSITIVE LOGITS
    åľ¨åİŁ
    0.09
     originals
    0.08
    ç¥ŀä¹ĭ
    0.08
    缸å½ĵäºİ
    0.08
     equivalents
    0.07
     equivalente
    0.07
     equivalent
    0.07
     Equivalent
    0.07
     ана
    0.07
    oods
    0.07
    Activations Density 0.180%

    No Known Activations