© 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. 41226
    Prev
    Next
    INDEX
    Explanations

    variable assignments, object properties

    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
    WARE
    -0.07
    ihe
    -0.07
    ])->
    -0.06
    ippo
    -0.06
    ogas
    -0.06
    igli
    -0.06
    çļĦéģĵçIJĨ
    -0.06
    ä¸įæķ£
    -0.06
    _pickle
    -0.06
    uli
    -0.06
    POSITIVE LOGITS
    ikit
    0.07
    itelist
    0.07
     amoureux
    0.07
    åħĭæĭī
    0.07
    ç¼ĸ审
    0.06
    é¦
    0.06
    èħĶ
    0.06
     ats
    0.06
    ica
    0.06
    atu
    0.06
    Activations Density 0.037%

    No Known Activations