© 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. 15718
    Prev
    Next
    INDEX
    Explanations

    abstract class

    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
    rze
    -0.08
    æ¹¾åĮº
    -0.08
    çİĩè¾¾
    -0.07
    AWN
    -0.07
    -default
    -0.07
    èĻŀ
    -0.07
    -inline
    -0.07
    quarter
    -0.07
    OSH
    -0.07
    latable
    -0.07
    POSITIVE LOGITS
    åĨ³å®ļæĺ¯åIJ¦
    0.07
    åħ¬åĪĨ
    0.07
     conform
    0.07
    åIJĦ个
    0.07
    æľªçŁ¥çļĦ
    0.06
    odont
    0.06
    åĽŀçŃĶ
    0.06
    roman
    0.06
    zan
    0.06
    åį·
    0.06
    Activations Density 0.089%

    No Known Activations