© 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. 7919
    Prev
    Next
    INDEX
    Explanations

    Defendant's case phases

    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
    ons
    -0.07
    le
    -0.06
     question
    -0.06
    èĦļä¸ĭ
    -0.06
    ad
    -0.06
     bez
    -0.06
    on
    -0.06
    art
    -0.06
     Weiss
    -0.06
    lee
    -0.06
    POSITIVE LOGITS
    ámos
    0.09
    è£ģå®ļ
    0.08
    ¬¸
    0.08
    çĽ¸çŁ¥
    0.08
    ecat
    0.08
    elve
    0.08
    intree
    0.08
    ä¸īä¸Ń
    0.08
     ripar
    0.08
    three
    0.08
    Activations Density 0.900%

    No Known Activations