© 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. 1811
    Prev
    Next
    INDEX
    Explanations

    see also

    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
    ç²Ĺ
    -0.08
    åīį款
    -0.08
    DOMNode
    -0.08
    opus
    -0.08
    illin
    -0.08
    Enlarge
    -0.07
    ủa
    -0.07
    équip
    -0.07
     pér
    -0.07
    urende
    -0.07
    POSITIVE LOGITS
    лей
    0.06
    ä¹±çļĦ
    0.06
     enf
    0.06
    ç³ľ
    0.06
    åºĶæľīçļĦ
    0.06
    ggi
    0.06
    templ
    0.06
    avic
    0.06
    TEL
    0.05
    avor
    0.05
    Activations Density 0.002%

    No Known Activations