© 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. 33725
    Prev
    Next
    INDEX
    Explanations

    by or using

    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
    æŃ£ç¡®åľ°
    -0.07
    æĺ¯ä»¥
    -0.07
    ²
    -0.06
     Col
    -0.06
    ester
    -0.06
    ড়
    -0.06
    便åĪ©
    -0.06
    Ī
    -0.06
     withd
    -0.06
    ellate
    -0.06
    POSITIVE LOGITS
    çªŁ
    0.08
    shed
    0.08
    uru
    0.07
    ncer
    0.07
    imak
    0.07
    YST
    0.07
    uern
    0.07
    æ¯ħ
    0.07
    azu
    0.07
    ((&
    0.07
    Activations Density 0.001%

    No Known Activations