© 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. 47881
    Prev
    Next
    INDEX
    Explanations

    guide, master, reliable, strict, essay, assistance

    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
    estream
    -0.08
    asket
    -0.08
     Biro
    -0.08
    å°¼æĸ¯
    -0.08
    [dim
    -0.07
     nowhere
    -0.07
    rophe
    -0.07
    etar
    -0.07
    гей
    -0.07
    ngh
    -0.07
    POSITIVE LOGITS
     &
    0.06
    LAB
    0.06
    èĬ±çļĦ
    0.06
     Vac
    0.06
    ura
    0.06
    ັàºĻ
    0.06
    ÷
    0.06
     Sure
    0.06
    ва
    0.06
     .
    0.05
    Activations Density 0.008%

    No Known Activations