© 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. 49406
    Prev
    Next
    INDEX
    Explanations

    cyclic, dimensional, Singleton

    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¸įä½ľ
    -0.08
    åIJĪçIJĨåľ°
    -0.08
    !!:
    -0.08
    رجاÙĦ
    -0.07
    ább
    -0.07
    áºŃp
    -0.07
    éĩįéĩįçļĦ
    -0.07
    atto
    -0.07
    æ±ĤçĶŁåŃĺ
    -0.07
    imbangan
    -0.07
    POSITIVE LOGITS
    /single
    0.08
    (single
    0.07
    omma
    0.07
    ard
    0.07
    åįķ项
    0.06
    ola
    0.06
    .pa
    0.06
    éĶ¥
    0.06
     spit
    0.06
    (mon
    0.06
    Activations Density 0.010%

    No Known Activations