© 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. 19260
    Prev
    Next
    INDEX
    Explanations

    effective

    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
    ardin
    -0.07
    æĹłæĤĶ
    -0.07
    otify
    -0.07
    å¤§æľ¬èIJ¥
    -0.07
    åģ¶
    -0.07
     classified
    -0.06
    å®ļçĤ¹
    -0.06
     senz
    -0.06
    åĴĮè¦ģæ±Ĥ
    -0.06
     सà¥ĭ
    -0.06
    POSITIVE LOGITS
     effective
    0.08
     tunes
    0.08
    breadcrumbs
    0.08
     incorporates
    0.08
     incorporating
    0.08
    effective
    0.07
     incorporate
    0.07
    ahrungs
    0.07
    çļĦæľīæķĪ
    0.07
     Effective
    0.07
    Activations Density 0.012%

    No Known Activations