© 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. 55951
    Prev
    Next
    INDEX
    Explanations

    title or article headings

    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
     Klar
    -0.07
    rade
    -0.07
     Fertig
    -0.07
    eton
    -0.07
    使çĶ¨åīį
    -0.07
    ecat
    -0.06
    å¯¹ä½łçļĦ
    -0.06
    ä¹ĭåīį
    -0.06
    isper
    -0.06
    acar
    -0.06
    POSITIVE LOGITS
    antina
    0.08
    bant
    0.08
    ×IJ×ķת
    0.08
     bur
    0.08
    aduras
    0.07
    uchu
    0.07
    åīį款
    0.07
     (('
    0.07
    (strtolower
    0.07
    俨çĦ¶
    0.07
    Activations Density 0.030%

    No Known Activations