© 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. 23883
    Prev
    Next
    INDEX
    Explanations

    find solutions or steps

    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
    alon
    -0.07
    .outer
    -0.06
    亲亲
    -0.06
     Relevant
    -0.06
    æ£Ĵæ£Ĵ
    -0.06
    QA
    -0.06
     Compar
    -0.06
    ä¹ı
    -0.05
     sweeps
    -0.05
     VA
    -0.05
    POSITIVE LOGITS
    å¦Ĥæŀľåıijçİ°
    0.10
    å¦Ĥæŀľä¸įèĥ½
    0.09
    æĺ¯åIJ¦åŃĺåľ¨
    0.09
    idé
    0.08
    ä¸ĢæŦåıijçİ°
    0.08
    reu
    0.08
    åı¯è¡ĮçļĦ
    0.08
    лÑij
    0.08
     succeed
    0.08
    odable
    0.08
    Activations Density 0.012%

    No Known Activations