© 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. 38104
    Prev
    Next
    INDEX
    Explanations

    protocol and related technical terms

    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
    ments
    -0.09
    ened
    -0.09
    nez
    -0.08
    è¨ĢãģĪãģ°
    -0.08
    fold
    -0.08
    appropri
    -0.08
    abouts
    -0.08
    OrUpdate
    -0.07
    heits
    -0.07
    dade
    -0.07
    POSITIVE LOGITS
    matic
    0.10
    ÏĦαι
    0.09
    onial
    0.08
    itical
    0.08
    ypse
    0.08
    à¸ģารà¸ĵà¹Į
    0.08
    æĢ§åľ°
    0.07
    empa
    0.07
    ¥
    0.07
    ovolta
    0.07
    Activations Density 0.033%

    No Known Activations