© 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. 12539
    Prev
    Next
    INDEX
    Explanations

    picking without replacement

    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
     otherwise
    -0.08
    pars
    -0.07
    æĺ¥èĬ±
    -0.07
    -binary
    -0.07
    ORK
    -0.07
    ÙĪاÙħ
    -0.07
    åij¨æľŁæĢ§
    -0.07
    emode
    -0.07
    iner
    -0.07
    binary
    -0.07
    POSITIVE LOGITS
    æĮij
    0.09
     pick
    0.09
     nig
    0.08
    .pick
    0.08
     depleted
    0.08
    å·²ç»ı没æľī
    0.07
    çĻ¾éĩĮ
    0.07
    à¹ģร
    0.07
     Elo
    0.07
    éĢĤåºĶäºĨ
    0.07
    Activations Density 0.014%

    No Known Activations