© 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. 38659
    Prev
    Next
    INDEX
    Explanations

    following adverbs and prepositions

    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
    foundland
    -0.10
    zeria
    -0.09
    lipse
    -0.09
    rafa
    -0.08
    gnore
    -0.08
    ascript
    -0.08
    amerate
    -0.08
    racji
    -0.08
    toon
    -0.08
    AndView
    -0.08
    POSITIVE LOGITS
    ad
    0.07
    _
    0.07
    0.06
    AD
    0.06
    P
    0.06
    B
    0.06
    b
    0.05
    C
    0.05
    M
    0.05
    c
    0.05
    Activations Density 0.301%

    No Known Activations