© 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. 27833
    Prev
    Next
    INDEX
    Explanations

    provide basis for

    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
    ä¸Ģ念
    -0.07
    roż
    -0.07
    为äºĨ
    -0.06
    utable
    -0.06
    ubar
    -0.06
    æ°ijåħµ
    -0.06
    umah
    -0.06
     모ìĬµ
    -0.06
    çĶ·çļĦ
    -0.06
    lieb
    -0.06
    POSITIVE LOGITS
    çĶ¨æĪ·æıIJä¾Ľ
    0.12
    客æĪ·æıIJä¾Ľ
    0.10
    ä¼ģä¸ļæıIJä¾Ľ
    0.09
    æŃ¤èµ·
    0.09
    åį³å°ĨåĪ°æĿ¥çļĦ
    0.09
    æĹ¥åIJİ
    0.09
    ç©©
    0.08
     unsus
    0.08
    ä½ķåľ¨
    0.08
    å¢ŀæ·»äºĨ
    0.07
    Activations Density 0.008%

    No Known Activations