© 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. 43549
    Prev
    Next
    INDEX
    Explanations

    cost of tickets, monthly food

    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
    å¤§åĽ¾
    -0.08
     رغ
    -0.07
    稽
    -0.07
    çģµå¼Ĥ
    -0.07
    æĢĢä¸Ń
    -0.07
     plage
    -0.07
    :Object
    -0.07
    agnol
    -0.07
     eind
    -0.07
    avat
    -0.07
    POSITIVE LOGITS
    è¾Ł
    0.07
    _strategy
    0.07
    åħį
    0.06
    DEX
    0.06
     Klan
    0.06
    éļĶ
    0.06
    æĸ¯çī¹
    0.06
     اض
    0.06
    lg
    0.06
    è·¨åĮºåŁŁ
    0.06
    Activations Density 0.030%

    No Known Activations