© 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. 16675
    Prev
    Next
    INDEX
    Explanations

    coordinates and data points

    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
    两å¤Ħ
    -0.08
    两èĢħ
    -0.07
    æľįåĬ¡ä¿Ŀéļľ
    -0.06
    åģļçļĦæĺ¯
    -0.06
    åĵªåĦ¿
    -0.06
     whichever
    -0.06
    éĤ£åĦ¿
    -0.06
    atore
    -0.06
    ent
    -0.06
     ìĺ¤ë¥´
    -0.06
    POSITIVE LOGITS
    swick
    0.09
     altrett
    0.09
    IOC
    0.08
    prus
    0.08
    yli
    0.08
    ioc
    0.08
    åºĶ该æĢİä¹Ī
    0.07
    ,default
    0.07
    ÅĽc
    0.07
    ä¸ĭåIJĮ
    0.07
    Activations Density 0.030%

    No Known Activations