© 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. 45720
    Prev
    Next
    INDEX
    Explanations

    in the case of

    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
    åħ¶æŀĹ
    -0.08
    forte
    -0.08
    ä¸İåѦçĶŁ
    -0.08
    Recovered
    -0.07
    åħ¶å®ĥçļĦ
    -0.07
    åıªä»£è¡¨
    -0.07
    åĢ¼å¾Ĺä¹°
    -0.07
    _SUP
    -0.07
    æıIJä¾ĽæĽ´åĬł
    -0.07
    legen
    -0.07
    POSITIVE LOGITS
    ubar
    0.08
     данном
    0.07
    æĹ¶ä¸º
    0.06
    ä»ĬåĽŀãģ¯
    0.06
    ickl
    0.06
    æľīè¿Ļ个
    0.06
    ä¾ĭåŃIJ
    0.06
    ersen
    0.06
    insky
    0.06
    jem
    0.06
    Activations Density 0.036%

    No Known Activations