© 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. 3677
    Prev
    Next
    INDEX
    Explanations

    research papers and technical terms

    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
    çīĪæĿĥå½ĴåİŁä½ľèĢħæīĢæľī
    -0.07
     Haven
    -0.07
    å¼¥
    -0.07
    å¹³åĿ¦
    -0.07
    rone
    -0.07
    èī¯
    -0.06
    Grab
    -0.06
     daw
    -0.06
    aises
    -0.06
    å·¦
    -0.06
    POSITIVE LOGITS
    [J
    0.09
    åħ®
    0.08
    åħ³äºİåį°åıij
    0.07
    .obtain
    0.07
    //:
    0.07
    è¢ŃæĿ¥
    0.06
     versus
    0.06
    ä»Ģä¹ĪæĥħåĨµ
    0.06
    .pdf
    0.06
    ','%
    0.06
    Activations Density 0.306%

    No Known Activations