© 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. 4272
    Prev
    Next
    INDEX
    Explanations

    subtype, type, phenotype differences

    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
    Ìģ
    -0.07
    æłĸ
    -0.06
    åįģäºĮçĶŁèĤĸ
    -0.06
    çĶŁåŃIJ
    -0.06
    åģī
    -0.06
    没æ³ķ
    -0.06
    ä¸įæľ½
    -0.06
     fate
    -0.06
    SCP
    -0.06
    æľīä»Ģä¹ĪçĶ¨
    -0.06
    POSITIVE LOGITS
     cases
    0.09
     variantes
    0.09
    å±ŀå®ŀ
    0.09
    åĩĨç¡®æĬĬæı¡
    0.09
     variante
    0.08
    vole
    0.08
    辨åĪ«
    0.08
     subtype
    0.08
    è¯ĬæĸŃ为
    0.08
     variants
    0.08
    Activations Density 0.009%

    No Known Activations