© 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. 49637
    Prev
    Next
    INDEX
    Explanations

    cases like Mapp

    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
    楣
    -0.08
    azon
    -0.07
     Ø®ÙĦاÙĦÙĩ
    -0.07
    å½¼
    -0.06
    ise
    -0.06
    è¢į
    -0.06
    azor
    -0.06
    æĪijçŁ¥éģĵäºĨ
    -0.06
    áĥĶáĥĹ
    -0.06
     Ø®ÙĦاÙĦÙĩا
    -0.06
    POSITIVE LOGITS
    ãģķãģ¦
    0.09
    ä¸ĩå²ģ
    0.08
    olino
    0.08
    ãģ¨ãģĵãĤįãģ§
    0.07
    å½ĵãģŁãĤĬ
    0.07
    trand
    0.07
    Parts
    0.07
    å¤ĸ人
    0.07
    è¿ĶåĽŀ顶éĥ¨
    0.07
     Wrapped
    0.06
    Activations Density 0.366%

    No Known Activations