© 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. 21320
    Prev
    Next
    INDEX
    Explanations

    acts, constitution, organism, scene, selection

    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
     però
    -0.09
    kaar
    -0.08
    ��
    -0.08
     ÏĮμÏīÏĤ
    -0.08
     rasse
    -0.08
    带æĪijåİ»
    -0.08
    º¼
    -0.08
    äºĨ解ä¸Ģä¸ĭåIJ§
    -0.08
     filosof
    -0.07
     جداÙĭ
    -0.07
    POSITIVE LOGITS
    -
    0.08
    -,
    0.08
    —as
    0.08
     arguably
    0.08
    æĬijæĪĸ
    0.08
     _
    0.08
    —in
    0.07
    Âł
    0.07
     perhaps
    0.07
     presumably
    0.07
    Activations Density 0.120%

    No Known Activations