© 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. 50370
    Prev
    Next
    INDEX
    Explanations

    sliding with follow-up words

    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
    isman
    -0.08
    hardt
    -0.07
    igsaw
    -0.07
    elon
    -0.07
    ITIES
    -0.07
    OfWork
    -0.07
    schaft
    -0.07
    metic
    -0.07
    utral
    -0.07
    ities
    -0.07
    POSITIVE LOGITS
    pery
    0.08
    /sl
    0.08
    èĩªå¦Ĥ
    0.08
    into
    0.08
    t
    0.08
    irectory
    0.07
    ä¸įåīį
    0.07
     Barbosa
    0.07
    Ĭ
    0.07
    own
    0.07
    Activations Density 0.026%

    No Known Activations