© 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. 4450
    Prev
    Next
    INDEX
    Explanations

    parameter estimation for models

    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
    agram
    -0.08
    à¤ķà¥įरम
    -0.07
     congratulations
    -0.07
    å¥ļ
    -0.07
    ugu
    -0.07
    Äįnost
    -0.07
    HOR
    -0.07
    .gnu
    -0.07
     effortless
    -0.06
    ìĦĿ
    -0.06
    POSITIVE LOGITS
     realistic
    0.11
     estim
    0.10
     realism
    0.10
     modeling
    0.10
    åIJĪçIJĨ
    0.09
     estimate
    0.09
     reasonable
    0.09
    reasonable
    0.09
     based
    0.09
     assumptions
    0.09
    Activations Density 0.036%

    No Known Activations