© 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. 4254
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and code

    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
    anes
    -0.07
    nus
    -0.07
    aus
    -0.06
    ecu
    -0.06
    unis
    -0.06
    stats
    -0.06
    aa
    -0.06
    eks
    -0.06
    fie
    -0.06
    nos
    -0.06
    POSITIVE LOGITS
    äch
    0.08
    berge
    0.08
    家éŨåı£
    0.08
    turut
    0.08
    äºĨåı£æ°Ķ
    0.08
    onio
    0.07
    åĢĴäºĨ
    0.07
    ÄĻcz
    0.07
    è¶ħ
    0.07
    ancock
    0.07
    Activations Density 0.003%

    No Known Activations