© 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. 49188
    Prev
    Next
    INDEX
    Explanations

    listen to

    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
    iled
    -0.10
    ials
    -0.09
     Ñģобой
    -0.09
    nitz
    -0.09
    ĺ
    -0.09
    à¹Īà¸ĩ
    -0.08
    holders
    -0.08
    ially
    -0.08
    оÑĢга
    -0.07
    æĪŁ
    -0.07
    POSITIVE LOGITS
    ä¸ĢåIJ¬
    0.09
    ings
    0.09
    æĤ¦èĢ³
    0.08
    é£İ声
    0.08
    /read
    0.08
    bird
    0.08
    åĩłå£°
    0.08
    erra
    0.08
    èĢ³è¾¹
    0.08
     heard
    0.08
    Activations Density 0.084%

    No Known Activations