© 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. 33997
    Prev
    Next
    INDEX
    Explanations

    Lai or ai

    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
    اÙĭ
    -0.10
    lah
    -0.10
    Ùħ
    -0.09
    ly
    -0.09
    micas
    -0.09
    nya
    -0.08
    ors
    -0.08
    ł
    -0.08
    ìľ¼ë¡ľ
    -0.08
    nieuw
    -0.08
    POSITIVE LOGITS
    /of
    0.09
    pton
    0.09
    abouts
    0.09
    izabeth
    0.08
    /from
    0.07
    inds
    0.07
    istic
    0.07
    ÑģÑĤв
    0.07
    /by
    0.07
    ÙĴÙĨ
    0.07
    Activations Density 0.004%

    No Known Activations