© 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. 49316
    Prev
    Next
    INDEX
    Explanations

    probability distributions

    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
    ellone
    -0.08
    epass
    -0.08
     counter
    -0.08
    åĿIJ车
    -0.08
    -counter
    -0.07
    ÙĨاÙĪÙĦ
    -0.07
    åijĺçļĦ
    -0.07
    çĥŃéŨæłĩçŃ¾
    -0.07
    comm
    -0.07
    orough
    -0.07
    POSITIVE LOGITS
    æĬ½
    0.08
    ä¸Ģç¬ij
    0.07
    Aj
    0.07
     probabilities
    0.07
    pie
    0.07
    liers
    0.07
    æľīçĶŁ
    0.06
    istributions
    0.06
     Prob
    0.06
    ä¸ĢæŶéĹ´
    0.06
    Activations Density 0.004%

    No Known Activations