© 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. 49048
    Prev
    Next
    INDEX
    Explanations

    of which they are a part

    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
    éĻ¤
    -0.08
    hias
    -0.07
    åĴĮæľ¬
    -0.07
    ontos
    -0.07
    å¦Ĥçģ«
    -0.07
    adero
    -0.07
    riez
    -0.07
    æ»ĵ
    -0.06
    rale
    -0.06
    .stringValue
    -0.06
    POSITIVE LOGITS
    ä¸İä¹ĭ
    0.20
    åħ¶æīĢ
    0.17
     therein
    0.17
     underlying
    0.17
     associated
    0.17
     accompanying
    0.15
    åľ¨åħ¶ä¸Ń
    0.15
     thereof
    0.14
    éļıä¹ĭ
    0.14
    å®ĥæīĢ
    0.14
    Activations Density 0.668%

    No Known Activations