© 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. 56598
    Prev
    Next
    INDEX
    Explanations

    agonists and usage

    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
    iz
    -0.07
    or
    -0.06
    éĩĩçĶ¨
    -0.06
    ley
    -0.06
     Miz
    -0.06
    se
    -0.06
     ref
    -0.06
     latin
    -0.06
    as
    -0.06
    ors
    -0.06
    POSITIVE LOGITS
    chetta
    0.10
    çĽĸä¸ĸ
    0.09
    uman
    0.09
     Hawkins
    0.08
    ÑĤаки
    0.08
    åı¤å±ĭ
    0.08
    xAC
    0.08
    产åĵģçłĶåıij
    0.08
    ubl
    0.08
    omÄĽ
    0.08
    Activations Density 0.364%

    No Known Activations