© 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. 50136
    Prev
    Next
    INDEX
    Explanations

    after you

    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
    -feature
    -0.07
    ervi
    -0.07
    ήμε
    -0.07
    æĨĶæĤ´
    -0.07
    andid
    -0.07
    jemu
    -0.06
    åħ¶çī¹å¾ģ
    -0.06
    Latest
    -0.06
    ists
    -0.06
    eced
    -0.06
    POSITIVE LOGITS
    fo
    0.07
    apta
    0.07
    çĻ»
    0.07
    å°±ä½į
    0.07
     raff
    0.07
     Blackburn
    0.06
     fo
    0.06
    asin
    0.06
    .EventHandler
    0.06
     counters
    0.06
    Activations Density 0.202%

    No Known Activations