© 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. 65235
    Prev
    Next
    INDEX
    Explanations

    public static

    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
     POD
    -0.07
    sel
    -0.06
    foundland
    -0.06
    itants
    -0.06
    çĬ¹
    -0.06
     foc
    -0.06
    æĭ¥
    -0.06
    upas
    -0.06
    ׳×ķת
    -0.06
    rans
    -0.05
    POSITIVE LOGITS
    eated
    0.08
    oka
    0.08
    anan
    0.07
    ä¸ŃåŃĹ
    0.07
    orum
    0.07
    rete
    0.07
    Occurred
    0.07
    ITA
    0.07
    orest
    0.07
    osed
    0.07
    Activations Density 0.167%

    No Known Activations