© 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. 12916
    Prev
    Next
    INDEX
    Explanations

    game or bar

    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
    æ¾ľ
    -0.07
    agg
    -0.06
     unc
    -0.06
     Kaplan
    -0.06
    abilia
    -0.06
    ião
    -0.06
     ################################
    -0.06
    çĬĢçīĽ
    -0.06
    å¾ħ
    -0.06
    zl
    -0.06
    POSITIVE LOGITS
    ÃŃž
    0.08
    ÏĢά
    0.08
    igor
    0.07
    omag
    0.07
    udir
    0.07
     ãĤ¹ãĥĿãĥ³ãĤµãĥ¼ãĤµãĤ¤ãĥĪ
    0.07
    asl
    0.07
    à¦ļà§ĩ
    0.07
    ä¸Ģåı¶
    0.07
    .fm
    0.07
    Activations Density 0.027%

    No Known Activations