© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 2065
    Prev
    Next
    INDEX
    Explanations

    how /

    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
    ...).
    -0.09
    [__
    -0.08
    ...",
    -0.08
    ...,
    -0.08
    )").
    -0.08
    iar
    -0.08
     >(
    -0.08
    erat
    -0.07
     (*(
    -0.07
    )').
    -0.07
    POSITIVE LOGITS
    azu
    0.08
    иÑĤо
    0.07
    人ä¸Ģ
    0.07
    ковÑģкого
    0.07
    éĹ®é¢ĺåĪĨæŀIJ
    0.07
    æ±Łå¸Ĥ
    0.07
    ihu
    0.06
     rented
    0.06
    ’’
    0.06
    ái
    0.06
    Activations Density 0.075%

    No Known Activations