© 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. 34056
    Prev
    Next
    INDEX
    Explanations

    weight and mass units

    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
    okus
    -0.08
    edenk
    -0.08
    зÑĮ
    -0.08
    erder
    -0.08
    hots
    -0.08
    çīĻåĪ·
    -0.08
    éķ¿ç¯ĩ
    -0.08
    ä¸īæľĪ
    -0.08
    edges
    -0.08
    Interpolator
    -0.07
    POSITIVE LOGITS
    éĩįéĩı
    0.20
     weight
    0.20
    çļĦéĩįéĩı
    0.18
     weights
    0.18
    weight
    0.17
     Weight
    0.16
    ä½ĵéĩį
    0.16
    Weight
    0.16
     heavier
    0.15
    -weight
    0.15
    Activations Density 0.103%

    No Known Activations