© 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. 34475
    Prev
    Next
    INDEX
    Explanations

    permission, blogging, salt, please

    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
    æĽ´åħ¨
    -0.08
     dicip
    -0.08
    à¸Ļà¸Ļ
    -0.07
    usas
    -0.07
    OperationException
    -0.07
    å¦Ĥæŀľå¤§å®¶
    -0.07
    {\"
    -0.07
    ãģĻãģĻ
    -0.07
    isse
    -0.07
    stein
    -0.07
    POSITIVE LOGITS
    综ä¸ĬæīĢè¿°
    0.06
     recons
    0.06
    éĢļè¿ĩ以ä¸Ĭ
    0.06
     manifold
    0.06
    man
    0.06
     proprio
    0.06
    éĤ£é¢Ĺ
    0.06
     assorted
    0.05
     sidew
    0.05
    æĽ¼
    0.05
    Activations Density 0.001%

    No Known Activations