© 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. 33946
    Prev
    Next
    INDEX
    Explanations

    often asked

    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
    çĹħéŃĶ
    -0.07
    顺å¿ĥ
    -0.07
    ubs
    -0.07
    æĹ¢çĦ¶æĺ¯
    -0.07
    æľīä»»ä½ķ
    -0.07
    çīµ
    -0.07
     kellett
    -0.07
    æݸ
    -0.07
    ackson
    -0.07
    è±ģ
    -0.07
    POSITIVE LOGITS
    å¾Ģå¾Ģ
    0.16
     often
    0.14
    å¾Ģå¾Ģæĺ¯
    0.13
     incorrectly
    0.13
     Often
    0.13
     mistakenly
    0.12
    误åĮº
    0.12
     wrongly
    0.12
     spesso
    0.12
     errone
    0.12
    Activations Density 0.570%

    No Known Activations