© 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. 57256
    Prev
    Next
    INDEX
    Explanations

    final version

    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
    pera
    -0.10
    æĸ°å±Ģ
    -0.09
    ucceed
    -0.08
    ande
    -0.08
    eters
    -0.08
    едÑĥ
    -0.08
    avance
    -0.08
    eldon
    -0.07
    jenigen
    -0.07
    oved
    -0.07
    POSITIVE LOGITS
    ity
    0.11
    eness
    0.09
    istir
    0.09
    rophe
    0.09
    iza
    0.09
    «
    0.08
    issima
    0.08
    -most
    0.08
    izing
    0.08
    ividual
    0.08
    Activations Density 0.026%

    No Known Activations