© 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. 46318
    Prev
    Next
    INDEX
    Explanations

    exponent

    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
    ness
    -0.12
    NESS
    -0.12
    ellaneous
    -0.09
    abouts
    -0.09
    ulich
    -0.08
    gaard
    -0.08
     mạc
    -0.08
    ÙĤات
    -0.08
    gether
    -0.08
    celona
    -0.07
    POSITIVE LOGITS
    ively
    0.12
    iation
    0.11
    ials
    0.10
    iated
    0.10
    ãĥ³
    0.10
    iab
    0.10
    aal
    0.09
    à§Ģয়
    0.08
    ilogue
    0.08
    ized
    0.08
    Activations Density 0.005%

    No Known Activations