© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 42323
    Prev
    Next
    INDEX
    Explanations

    best practices, patient management, navigation

    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
    麻麻
    -0.07
    ansk
    -0.07
    anch
    -0.07
    orma
    -0.07
    ANDARD
    -0.07
    æĹłå½±
    -0.07
    :&
    -0.06
     Jakob
    -0.06
    eness
    -0.06
     (!((
    -0.06
    POSITIVE LOGITS
    çļ®ä¹¦
    0.08
    veys
    0.08
    änger
    0.07
    emento
    0.07
     Lies
    0.07
    phis
    0.07
    ösen
    0.07
    vey
    0.06
    dependency
    0.06
    çĬ¯
    0.06
    Activations Density 0.004%

    No Known Activations