© 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. 44960
    Prev
    Next
    INDEX
    Explanations

    Mapper

    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
    окÑģи
    -0.07
    ddy
    -0.07
    è¦ģæ±ĤåIJĦ
    -0.07
    å®īè£ħè°ĥè¯ķ
    -0.07
    mailto
    -0.07
    åħ¨éĻ¢
    -0.07
    äºĶåĪĨ
    -0.07
    et
    -0.07
    RESSED
    -0.06
    å·¥ä½ľè¿Ľè¡Į
    -0.06
    POSITIVE LOGITS
    éĤ£è¾¹
    0.10
    è¿Ļè¾¹çļĦ
    0.09
    è¿Ļè¾¹
    0.09
    éĤ£è¾¹çļĦ
    0.08
    å´İ
    0.07
     Mapper
    0.07
    æĺłå°Ħ
    0.07
    echs
    0.07
    vor
    0.07
    upy
    0.07
    Activations Density 0.010%

    No Known Activations