© 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. 20215
    Prev
    Next
    INDEX
    Explanations

    for

    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
    请åĪ°
    -0.07
    actly
    -0.07
    ziej
    -0.07
    è®ĵæĤ¨
    -0.07
    Otherwise
    -0.07
    èĭ±æĸĩåIJįåŃĹ
    -0.07
    éspedes
    -0.07
    imers
    -0.06
    วาย
    -0.06
     sonst
    -0.06
    POSITIVE LOGITS
    循
    0.08
    éĺħè¯»æľ¬æĸĩåīį
    0.08
    åħ¶ä¸Ńæľī
    0.07
     if
    0.07
    _=
    0.07
    åľ¨
    0.07
    åħ¶ä¸Ń
    0.07
    æĸ°çĶŁ
    0.07
    åĨįåĬłä¸Ĭ
    0.06
    åħ¶ä¸ŃæľĢ
    0.06
    Activations Density 0.325%

    No Known Activations