© 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. 48851
    Prev
    Next
    INDEX
    Explanations

    I 'm / have / want

    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
    ially
    -0.07
    ående
    -0.07
    æĪij常常
    -0.07
    irement
    -0.07
    ignet
    -0.07
    endiz
    -0.07
    entially
    -0.07
    åľ°å¹³
    -0.07
    ingly
    -0.07
    aigned
    -0.06
    POSITIVE LOGITS
    zelf
    0.10
    've
    0.08
    ä¹ĭæīĢ
    0.08
    'll
    0.08
    acob
    0.08
    Å¡tu
    0.08
     !**
    0.08
    self
    0.07
    ftet
    0.07
    elts
    0.07
    Activations Density 0.759%

    No Known Activations