© 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. 47382
    Prev
    Next
    INDEX
    Explanations

    math equations and documentation

    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
     getattr
    -0.07
    u
    -0.06
    åı«ä»Ģä¹Ī
    -0.06
    gut
    -0.06
    mts
    -0.06
    çīĩ
    -0.06
    áĥ£áĥł
    -0.06
    ereg
    -0.06
    Association
    -0.06
    çīĩä¸Ń
    -0.06
    POSITIVE LOGITS
    循
    0.09
    屯
    0.08
    æĶ¯
    0.07
    à¸Ĺี
    0.07
    æŃ£åĢ¼
    0.07
     DOCUM
    0.07
    æĬļ
    0.07
    äºĶ次
    0.07
    åħ°åį¡
    0.07
     Greatest
    0.07
    Activations Density 0.036%

    No Known Activations