© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 9040
    Prev
    Next
    INDEX
    Explanations

    ation-induced

    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
     Pekan
    -0.09
    ampak
    -0.08
    accion
    -0.08
    ç½ij讯
    -0.08
    éĶ¦æ¶Ľ
    -0.08
    å¹´ä¸ĢåŃ£åº¦
    -0.08
     ãĤ¹ãĥĿãĥ³ãĤµãĥ¼ãĤµãĤ¤ãĥĪ
    -0.08
    èݱ德
    -0.08
    locals
    -0.08
     Balik
    -0.08
    POSITIVE LOGITS
    »
    0.07
    zien
    0.07
    os
    0.07
    ar
    0.07
    éĩĮ
    0.07
    osing
    0.07
    quier
    0.06
    es
    0.06
    ä¹İ
    0.06
    osti
    0.06
    Activations Density 0.004%

    No Known Activations