© 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. 40713
    Prev
    Next
    INDEX
    Explanations

    e-cigarette, boot, burger, bag, hospital, clinic, worm

    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
     portions
    -0.07
    rists
    -0.07
    ä¸Ģä½ĵåĮĸ
    -0.06
    ä¸Ģä½ĵçļĦ
    -0.06
    ä¸Ģä½ĵåĮĸçļĦ
    -0.06
     cautel
    -0.06
     {?
    -0.06
    ro
    -0.06
    ség
    -0.06
    bÄĽ
    -0.06
    POSITIVE LOGITS
    æĪĸå¤ļ个
    0.13
    sWith
    0.10
    (s
    0.09
     cualquiera
    0.09
    stype
    0.09
    æľĪä¸Ĭ
    0.09
    æĬķèµĦæĪĸ
    0.09
    们çļĦ
    0.09
     somebody
    0.09
    æĪĸå¤ļ
    0.09
    Activations Density 1.175%

    No Known Activations