© 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. 18360
    Prev
    Next
    INDEX
    Explanations

    create a consolidated

    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
    dden
    -0.07
    vena
    -0.07
    deo
    -0.07
    è¿Ļç§įåģļæ³ķ
    -0.07
    _stub
    -0.07
    enis
    -0.07
    æ¸ħæ´Ĺå¹²åĩĢ
    -0.07
     Schon
    -0.07
    æŃ£æľ¬
    -0.07
    beck
    -0.06
    POSITIVE LOGITS
    æģ¶
    0.08
    merged
    0.07
    ornings
    0.07
    æĸ°çļĦ
    0.07
    æ¡Ī
    0.07
    mero
    0.07
    åįı
    0.07
    åIJĪ并
    0.07
    å©¿
    0.07
    æ··åIJĪ
    0.07
    Activations Density 0.026%

    No Known Activations