© 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. 40504
    Prev
    Next
    INDEX
    Explanations

    phone numbers and ISBNs

    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
     Tre
    -0.06
    éŃĶæľ¯
    -0.06
     vers
    -0.06
    ä¹°åįĸ
    -0.06
     Beard
    -0.06
    olec
    -0.06
    æį·
    -0.06
     Vers
    -0.06
    åįĥéĩĮ
    -0.06
    lyph
    -0.06
    POSITIVE LOGITS
    chenk
    0.09
    osti
    0.09
    ä»»åĩŃ
    0.08
    è§ģ人
    0.08
    izzano
    0.08
    娴
    0.07
    à¸Ĩ
    0.07
    èĨĽ
    0.07
    ANGAN
    0.07
    @Data
    0.07
    Activations Density 0.158%

    No Known Activations