© 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. 51591
    Prev
    Next
    INDEX
    Explanations

    count or _count

    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
    æ§Ľ
    -0.09
    zyw
    -0.09
    _INITIALIZER
    -0.08
    _MAY
    -0.07
    Initializer
    -0.07
     Slut
    -0.07
    Scalars
    -0.07
    ocols
    -0.07
    igest
    -0.07
    _INITIAL
    -0.07
    POSITIVE LOGITS
     count
    0.10
    count
    0.10
    -count
    0.09
    æľĢå¤ļçļĦ
    0.09
     Count
    0.08
    Count
    0.08
     counted
    0.08
     counting
    0.08
    _count
    0.08
    .Count
    0.08
    Activations Density 0.004%

    No Known Activations