© 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. 22522
    Prev
    Next
    INDEX
    Explanations

    buying into

    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
    èijĨ
    -0.06
    æģķ
    -0.06
    åħ¨çIJĥæľĢ大çļĦ
    -0.06
    intaan
    -0.06
    bury
    -0.06
    asis
    -0.06
    abat
    -0.06
     orb
    -0.06
    ılım
    -0.06
     اÙĦÙĪاØŃد
    -0.06
    POSITIVE LOGITS
     préc
    0.07
    adt
    0.07
    åĽ¾åĨĮ
    0.07
    äºĮèĥİ
    0.07
    è¯»æľ¬
    0.07
    iring
    0.07
    Touches
    0.07
    outu
    0.06
    cobra
    0.06
    iging
    0.06
    Activations Density 0.060%

    No Known Activations