© 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. 13877
    Prev
    Next
    INDEX
    Explanations

    eigenvalue or exponent

    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
    ifel
    -0.08
    çĻ¾å®¶
    -0.07
    _PHASE
    -0.07
     revend
    -0.07
    ucin
    -0.07
    å®ĮçĴ§
    -0.07
    ä¸ĸå¤ĸ
    -0.07
    /cc
    -0.07
     Bev
    -0.07
    हà¥ĩ
    -0.07
    POSITIVE LOGITS
     eigen
    0.09
     Bands
    0.08
     band
    0.08
     spectral
    0.07
    orest
    0.07
    ordnet
    0.07
    band
    0.07
    ãĥIJãĥ³ãĥī
    0.07
    _band
    0.07
    spect
    0.07
    Activations Density 0.007%

    No Known Activations