© 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. 18603
    Prev
    Next
    INDEX
    Explanations

    applications and requirements

    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
    ensp
    -0.08
    çĵ®
    -0.08
    loquent
    -0.08
    åĴĮå®ĮåĸĦ
    -0.08
    æĮĸæİĺåħ¬åı¸
    -0.07
    ÐijÐļ
    -0.07
    agrant
    -0.07
     kese
    -0.07
    opil
    -0.07
     reform
    -0.07
    POSITIVE LOGITS
    çĶ¨éĢĶ
    0.10
    åºĶçĶ¨åľºæĻ¯
    0.08
     requirements
    0.08
    çī¹å®ļçļĦ
    0.08
     Anforderungen
    0.08
    éľĢæ±ĤçļĦ
    0.08
    ä¸įåľ¨ä¹İ
    0.08
    éľĢæ±Ĥ
    0.08
     requiring
    0.08
     purposes
    0.08
    Activations Density 0.191%

    No Known Activations