© 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. 46891
    Prev
    Next
    INDEX
    Explanations

    certain way

    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
    æľĢæ·±çļĦ
    -0.07
    lament
    -0.07
    æĺ¯çĶ¨
    -0.06
    à¸Ķา
    -0.06
    pas
    -0.06
    rade
    -0.06
    rava
    -0.06
    _pas
    -0.06
    č↵č↵
    -0.06
    ä¹ĭä½ľ
    -0.06
    POSITIVE LOGITS
     indeed
    0.09
     itulah
    0.08
    æ¯Ķåݻ年åIJĮæľŁ
    0.08
    è¿ĻæŃ£æĺ¯
    0.08
     wÅĤaÅĽnie
    0.08
    StackSize
    0.07
     inilah
    0.07
     Apel
    0.07
     appunto
    0.07
    stig
    0.07
    Activations Density 0.003%

    No Known Activations