© 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. 43319
    Prev
    Next
    INDEX
    Explanations

    technical specifications

    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
    eper
    -0.07
    #w
    -0.07
    ä¹ĿéľĦ
    -0.07
    ToOne
    -0.07
    å¹³åĿĩæ¯ı
    -0.07
    ζί
    -0.07
     вÑģкÑĢÑĭ
    -0.06
    æĪĺåľºä¸Ĭ
    -0.06
    æķĻå¸Ī们
    -0.06
    ä¸Ģ个æĺŁæľŁ
    -0.06
    POSITIVE LOGITS
    iphertext
    0.08
    தி
    0.07
    apu
    0.07
    èĩ´æķ¬
    0.07
    uela
    0.07
     overload
    0.07
    å¥īä¸Ĭ
    0.06
    æ¡IJ
    0.06
    çīĽ
    0.06
    -ton
    0.06
    Activations Density 0.004%

    No Known Activations