© 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. 20908
    Prev
    Next
    INDEX
    Explanations

    not including or excluding

    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
    hower
    -0.08
    å¾·æĭī
    -0.08
    éĩįè§Ĩ
    -0.07
    adari
    -0.07
    wein
    -0.07
    lop
    -0.07
    çĶļèĩ³æľī
    -0.07
    çİ©å¾Ĺ
    -0.06
    nip
    -0.06
    éºŁ
    -0.06
    POSITIVE LOGITS
    eteg
    0.08
    format
    0.07
    expo
    0.07
    飾
    0.07
     formatting
    0.07
    æ³ķå®ļ代表
    0.07
    åĽŀ车
    0.07
    etadata
    0.06
    _EXECUTE
    0.06
     trông
    0.06
    Activations Density 0.033%

    No Known Activations