© 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. 34530
    Prev
    Next
    INDEX
    Explanations

    differences between

    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
    uyo
    -0.08
    çĶĺ
    -0.08
    oyer
    -0.08
    èĥ§
    -0.07
    escu
    -0.07
    ä¸Ģ段æŶéĹ´çļĦ
    -0.06
    è¿ijå¹³
    -0.06
    ottie
    -0.06
    enso
    -0.06
     flat
    -0.06
    POSITIVE LOGITS
     differences
    0.23
    å·®å¼Ĥ
    0.22
     Differences
    0.20
     difference
    0.19
    çļĦå·®å¼Ĥ
    0.19
     diferenças
    0.18
    æĤ¬æ®Ĭ
    0.18
    difference
    0.18
     perbedaan
    0.18
     Perbedaan
    0.18
    Activations Density 0.125%

    No Known Activations