© 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. 23629
    Prev
    Next
    INDEX
    Explanations

    domains and contexts

    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
    thane
    -0.07
     billet
    -0.07
    Country
    -0.07
    ä½įç½®çļĦ
    -0.06
    jb
    -0.06
    çļĦ年代
    -0.06
     earm
    -0.06
    [:
    -0.06
    å°Ķå¾·
    -0.06
    éĺ¶æ®µæĢ§
    -0.06
    POSITIVE LOGITS
    osphere
    0.09
    å¹²éĥ¨éĺŁä¼į
    0.09
    à¹Īวà¸ĩ
    0.09
     workforce
    0.09
     realm
    0.09
     spectrum
    0.08
    éļĪ
    0.08
     arsenal
    0.08
    è¯Ħä»·ä½ĵç³»
    0.08
     vast
    0.08
    Activations Density 0.848%

    No Known Activations