© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 25113
    Prev
    Next
    INDEX
    Explanations

    Phys, J. Opt. Soc. Am. A

    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
    åĪĨä¸Ńå¿ĥ
    -0.08
     fór
    -0.08
    ennon
    -0.08
     Comer
    -0.08
    engel
    -0.08
    adena
    -0.08
    ahr
    -0.07
    å°Ķçī¹
    -0.07
    åIJĮ人
    -0.07
    ç§ģæĪ¿
    -0.07
    POSITIVE LOGITS
    串串
    0.07
    æĶ¿åºľåħ¬åijĬ
    0.07
    sms
    0.07
     ÙĨب
    0.06
     tick
    0.06
    оÑĢий
    0.06
    ä»Ģä¹ĪåİŁåĽł
    0.06
     رسÙħ
    0.06
     Consort
    0.06
    è·³åĪ°
    0.06
    Activations Density 0.008%

    No Known Activations