© 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. 44878
    Prev
    Next
    INDEX
    Explanations

    numbers, false, 4

    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
    ª
    -0.08
     incomplete
    -0.07
    è¿ŀçĿĢ
    -0.07
    ç²Ĺæļ´
    -0.07
    estro
    -0.07
     Ñħлоп
    -0.07
    ä¸įå®Įæķ´
    -0.07
    å±
    -0.07
    zyst
    -0.07
    Comple
    -0.07
    POSITIVE LOGITS
    =max
    0.08
    amax
    0.08
     whichever
    0.08
     Pare
    0.07
    å»Ĭ
    0.07
    è¦ģéĢīæĭ©
    0.07
    è§ħ
    0.07
    ä¼ļéĢīæĭ©
    0.07
    ç¡®å®ļ为
    0.07
     sclerosis
    0.07
    Activations Density 0.002%

    No Known Activations