© 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. 16705
    Prev
    Next
    INDEX
    Explanations

    must correspond, needs to be, should maintain

    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
    å¿ħå°Ĩ
    -0.09
    ниÑĩеÑģÑĤво
    -0.08
    æīįæľīäºĨ
    -0.08
    æķ°ä¸įæ¸ħ
    -0.08
    cind
    -0.08
    ustra
    -0.08
     forse
    -0.08
    [Int
    -0.08
    çĶļå°ij
    -0.07
    tram
    -0.07
    POSITIVE LOGITS
     be
    0.09
     ideally
    0.09
    asio
    0.08
    å°½åı¯èĥ½
    0.08
     möglichst
    0.07
    å°½åı¯èĥ½çļĦ
    0.07
    èĥ½å¤ŁæıIJä¾Ľ
    0.07
     Ideally
    0.07
    elta
    0.07
    ç»ıå¾Ĺèµ·
    0.07
    Activations Density 0.075%

    No Known Activations