© 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. 45514
    Prev
    Next
    INDEX
    Explanations

    familiarity and acquaintedness

    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
    manship
    -0.10
    agn
    -0.09
    avanaugh
    -0.09
    umer
    -0.08
    Formatter
    -0.07
    ikk
    -0.07
     Äijai
    -0.07
    agna
    -0.07
    ä¹ĭä¸ĢçļĦ
    -0.07
    antry
    -0.07
    POSITIVE LOGITS
    ç¨ĭ度
    0.10
    çĨŁæĤīçļĦ
    0.10
    ness
    0.10
    -looking
    0.09
    NESS
    0.09
     acquainted
    0.08
    çĨŁæĤī
    0.08
    ä¸įçĨŁæĤī
    0.08
     familiar
    0.08
    度é«ĺ
    0.08
    Activations Density 0.052%

    No Known Activations