© 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. 65291
    Prev
    Next
    INDEX
    Explanations

    then followed by comma or pronoun

    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
    abella
    -0.09
    ãģ¾ãģ¾
    -0.09
    etheless
    -0.09
    ceau
    -0.08
    并æıIJ交
    -0.08
     tehát
    -0.08
    ----------------------------------------------------------------------
    -0.08
    andro
    -0.08
    øb
    -0.08
    <|box_end|>
    -0.08
    POSITIVE LOGITS
    vid
    0.06
    yto
    0.06
    çľ·
    0.06
    pres
    0.06
    ç¼¥
    0.06
    cert
    0.06
    æľīéĤ£ä¹Ī
    0.06
     "
    0.06
    ying
    0.06
    of
    0.06
    Activations Density 0.043%

    No Known Activations