© 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. 19337
    Prev
    Next
    INDEX
    Explanations

    words or unusual characters

    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
     justified
    -0.06
    åıijå±ķæĶ¹éĿ©å§Ķ
    -0.06
    auff
    -0.06
    azon
    -0.06
    æ»ĵ
    -0.06
    ÐŁÐ¾Ð´ÑĢобнее
    -0.06
     exempl
    -0.06
    åıijè¾¾
    -0.06
    ippers
    -0.06
     ÐŁÐ¾Ð´ÑĢобнее
    -0.06
    POSITIVE LOGITS
    isar
    0.09
    ÑĤÑĥÑģ
    0.08
    ontre
    0.08
    centage
    0.08
    å½ĵä½ł
    0.07
    뾨
    0.07
    RICT
    0.07
    å½ĵäºĨ
    0.07
     Ùħتعد
    0.07
    urat
    0.07
    Activations Density 0.066%

    No Known Activations