© 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. 21771
    Prev
    Next
    INDEX
    Explanations

    parallel vector, computing, processing, Ajax, plate

    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
    annis
    -0.12
    tlement
    -0.11
    zelf
    -0.10
    fulness
    -0.10
    yel
    -0.09
    ahui
    -0.09
    panse
    -0.09
    chter
    -0.09
    eor
    -0.09
    ktop
    -0.09
    POSITIVE LOGITS
    ness
    0.09
    ation
    0.09
     nhau
    0.09
    ÙĬØ©
    0.08
    -minded
    0.08
    ion
    0.07
    allel
    0.07
    ainen
    0.07
    idge
    0.07
    icularly
    0.07
    Activations Density 0.020%

    No Known Activations