© 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. 43140
    Prev
    Next
    INDEX
    Explanations

    brain based on context

    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
     menyar
    -0.09
    arity
    -0.09
    ityEngine
    -0.09
    ities
    -0.08
    edia
    -0.08
    anee
    -0.08
     diranc
    -0.08
    ingan
    -0.08
    gary
    -0.08
    ียà¸ĩ
    -0.08
    POSITIVE LOGITS
    stem
    0.08
    fuck
    0.08
     hemisphere
    0.07
    丸
    0.07
    ne
    0.07
    -
    0.06
    aches
    0.06
    åĴĮç»ıæµİ
    0.06
    quake
    0.06
    ry
    0.06
    Activations Density 0.071%

    No Known Activations