© 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. 62416
    Prev
    Next
    INDEX
    Explanations

    Here we says

    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
     –
    -0.08
    æī©å±ķèµĦæĸĻ
    -0.08
    ðŁ
    -0.08
    Âł
    -0.07
    `
    -0.07
    -0.06
    [
    -0.06
     Colle
    -0.06
     Buffet
    -0.06
    æĸ¹éĿ¢
    -0.06
    POSITIVE LOGITS
    æľ¬åĪĬ
    0.10
    .ind
    0.10
    æľ¬çīĪ
    0.09
    rus
    0.09
     âĸ¶
    0.09
    Across
    0.09
    <|box_end|>
    0.09
    æı´æľĿ
    0.09
    rund
    0.08
    çī¹æ´¾
    0.08
    Activations Density 0.428%

    No Known Activations