© 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. 42599
    Prev
    Next
    INDEX
    Explanations

    pneumatic

    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
    ÑģÑı
    -0.09
    czyn
    -0.09
    jenigen
    -0.08
    ccoli
    -0.07
    -scenes
    -0.07
    sWith
    -0.07
    itored
    -0.07
    adies
    -0.07
    à§įড
    -0.07
    er
    -0.07
    POSITIVE LOGITS
    Ø©
    0.12
    uality
    0.10
    arella
    0.08
    reetings
    0.08
    imba
    0.08
    eneral
    0.08
    ic
    0.08
    iems
    0.07
    èĭ·
    0.07
    roupe
    0.07
    Activations Density 0.007%

    No Known Activations