© 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. 57537
    Prev
    Next
    INDEX
    Explanations

    delimited fields terminated by

    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
    borough
    -0.08
    AccessException
    -0.08
    ק×Ķ
    -0.08
     Bundy
    -0.08
    enheim
    -0.07
    baugh
    -0.07
    å¨ħ
    -0.07
    lassen
    -0.07
    οδο
    -0.07
    ĥģ
    -0.07
    POSITIVE LOGITS
     defaulted
    0.08
     default
    0.08
     defaults
    0.08
    defaults
    0.08
    default
    0.08
    é»ĺ
    0.08
    é»ĺ认çļĦ
    0.07
     trùng
    0.07
     DEFAULT
    0.07
    约å®ļ
    0.07
    Activations Density 0.084%

    No Known Activations