© 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. 41769
    Prev
    Next
    INDEX
    Explanations

    email addresses or protected content

    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
    åħļå§Ķå§Ķåijĺ
    -0.08
    âĢ§
    -0.07
    ackers
    -0.07
    abra
    -0.07
    kait
    -0.07
    ãĤ³ãĥŃ
    -0.07
    âĹĩâĹĨ
    -0.06
    ibat
    -0.06
     renc
    -0.06
    ÚĨÙĩ
    -0.06
    POSITIVE LOGITS
    TI
    0.07
    åĪĨä¹ĭä¸Ģ
    0.07
    tant
    0.06
    Ñĥго
    0.06
    æĶĺ
    0.06
    isset
    0.06
    lst
    0.06
    ียรà¹Į
    0.06
    usst
    0.06
    çĻŀ
    0.06
    Activations Density 0.108%

    No Known Activations