© 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. 15234
    Prev
    Next
    INDEX
    Explanations

    citations and code snippets

    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
    firm
    -0.07
    æī¹
    -0.06
    çī¹
    -0.06
    YL
    -0.06
    T
    -0.06
    ounds
    -0.06
     rá
    -0.06
    oire
    -0.06
     Cruc
    -0.06
    é½
    -0.06
    POSITIVE LOGITS
     pouc
    0.08
     повÑĸд
    0.08
     csajok
    0.08
    ENER
    0.08
    roda
    0.08
    æīĢå±ŀåĪĨç±»
    0.08
     abbig
    0.07
    ugh
    0.07
    apons
    0.07
    ï¼Ĭï¼Ĭï¼Ĭï¼Ĭï¼Ĭï¼Ĭï¼Ĭï¼Ĭ
    0.07
    Activations Density 1.372%

    No Known Activations