© 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. 10088
    Prev
    Next
    INDEX
    Explanations

    omitted or not shown

    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
    áĢĦáĢºáĢ¸
    -0.08
    æīįæľīåı¯èĥ½
    -0.08
     terlepas
    -0.07
    æµ®çĶŁ
    -0.07
    olare
    -0.07
    clair
    -0.07
    dol
    -0.07
    åĨħ容æıIJä¾Ľæĸ¹
    -0.07
    COPE
    -0.07
    полÑĥ
    -0.07
    POSITIVE LOGITS
    esel
    0.07
    anto
    0.07
     Suff
    0.06
    åħ·
    0.06
    antz
    0.06
    anson
    0.06
    æѤç§į
    0.06
    ãģ¾ãģĹãģ¦
    0.06
    пли
    0.06
    rov
    0.06
    Activations Density 0.047%

    No Known Activations