© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17578
    Prev
    Next
    INDEX
    Explanations

    moment of mass or expectation

    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
    bane
    -0.08
    rund
    -0.07
    Scoped
    -0.07
    andong
    -0.07
    .inflate
    -0.07
     godere
    -0.07
    ampe
    -0.07
    å·®ãģĹ
    -0.07
     bufsize
    -0.07
    Abort
    -0.07
    POSITIVE LOGITS
     weighted
    0.09
    åĬłæĿĥ
    0.09
    weighted
    0.08
    éĩįå¿ĥ
    0.08
     centroid
    0.08
     weighting
    0.08
     centroids
    0.08
    centroid
    0.07
    åģı移
    0.07
     Redistribution
    0.07
    Activations Density 0.003%

    No Known Activations