© 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. 30895
    Prev
    Next
    INDEX
    Explanations

    partially removed or separated

    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
    ®
    -0.07
    èĢĮä¸įæĺ¯
    -0.06
    ç¾²
    -0.06
     Harrison
    -0.06
     Keeps
    -0.06
     تعÙĦÙħ
    -0.06
    ä¿ĿæĮģåľ¨
    -0.06
    ç¥Ģ
    -0.05
    è¿ľç¦»
    -0.05
    æľīä½Ļ
    -0.05
    POSITIVE LOGITS
    ç½ĹæĽ¼
    0.09
     наконеÑĨ
    0.09
     finally
    0.09
    çļĦæŶåĢĻäºĨ
    0.09
    çĵ£
    0.08
    pell
    0.08
     dần
    0.08
    finally
    0.08
     converts
    0.08
     converting
    0.08
    Activations Density 0.242%

    No Known Activations