© 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. 40203
    Prev
    Next
    INDEX
    Explanations

    input data or structure

    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
    åı£çļĦ
    -0.07
    æĺĮå¹³
    -0.06
    ç²Ĵ
    -0.06
    -flow
    -0.06
    coni
    -0.06
     dependable
    -0.06
    Decl
    -0.06
    渺
    -0.06
     Decl
    -0.06
    åij³çĶĺ
    -0.06
    POSITIVE LOGITS
    forge
    0.09
    locales
    0.08
    киÑĪе
    0.08
    á»ĩm
    0.07
    ếng
    0.07
    æĮīè¦ģæ±Ĥ
    0.07
     ÑĥмÑĭ
    0.07
     ÙĪآخر
    0.07
    takt
    0.07
    ONSE
    0.07
    Activations Density 0.010%

    No Known Activations