© 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. 60792
    Prev
    Next
    INDEX
    Explanations

    mastering or mastery

    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
    áºŃy
    -0.10
    ustom
    -0.09
    à§įযাল
    -0.09
    rouch
    -0.08
    ality
    -0.08
    ésar
    -0.08
    verso
    -0.08
    ़
    -0.08
    ally
    -0.08
    HeaderView
    -0.08
    POSITIVE LOGITS
    çģ«åĢĻ
    0.08
    åĪĨ寸
    0.08
    æİ´
    0.07
    åħĪæľº
    0.07
    edException
    0.07
    OrFail
    0.07
    è¦ģé¢Ĩ
    0.07
    es
    0.07
    ments
    0.07
    edores
    0.06
    Activations Density 0.022%

    No Known Activations