© 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. 7909
    Prev
    Next
    INDEX
    Explanations

    stirring or agitation, including mixers

    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
    hood
    -0.08
    queeze
    -0.07
    ities
    -0.07
     tele
    -0.07
    eness
    -0.07
    å¢ĥåľ°
    -0.07
    ÏĦÎŃ
    -0.07
    enen
    -0.06
    åģļäºĭæĥħ
    -0.06
     measles
    -0.06
    POSITIVE LOGITS
    insky
    0.09
    ä¸įä¼ij
    0.09
    ä¸įæģ¯
    0.08
    ForResult
    0.08
    engel
    0.07
    äºĨåĩłä¸ĭ
    0.07
    lot
    0.07
    ots
    0.07
     incess
    0.07
    üssel
    0.07
    Activations Density 0.010%

    No Known Activations