© 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. 45230
    Prev
    Next
    INDEX
    Explanations

    creating .txt or file names

    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
    chy
    -0.09
    morph
    -0.08
    transforms
    -0.07
     Noon
    -0.07
    èIJ½æĪIJ
    -0.07
    çīĩçīĩ
    -0.07
    çĶŁä¸ĭ
    -0.07
    สาย
    -0.07
    æݨåĩºçļĦ
    -0.07
    æĹłæĤĶ
    -0.07
    POSITIVE LOGITS
    ä½
    0.08
    adÄĽ
    0.07
    åĢ
    0.07
     parseInt
    0.07
     gre
    0.07
     Fac
    0.06
     ÑģÑĥпеÑĢ
    0.06
     establishment
    0.06
    DET
    0.06
    ãĤ·ãĤ§ãĥ«
    0.06
    Activations Density 0.010%

    No Known Activations