© 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. 10273
    Prev
    Next
    INDEX
    Explanations

    spatial and temporal variation

    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
    _joint
    -0.08
    rawn
    -0.08
    zeiten
    -0.08
    ouw
    -0.08
    _times
    -0.08
    ноÑĢа
    -0.07
    Ñħоз
    -0.07
    eed
    -0.07
    诧
    -0.07
    ahir
    -0.07
    POSITIVE LOGITS
     toll
    0.07
    -ext
    0.06
    ç½Ĺæĭī
    0.06
     rod
    0.06
     stationary
    0.06
    assistant
    0.06
    åŃļ
    0.06
    roda
    0.06
    eka
    0.06
     Rod
    0.06
    Activations Density 0.030%

    No Known Activations