© 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. 40451
    Prev
    Next
    INDEX
    Explanations

    quantities and percentages

    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
    ãĥĬãĥ«
    -0.08
    äºĪ
    -0.07
     Lots
    -0.07
     Counts
    -0.06
    ena
    -0.06
    æĮ«
    -0.06
     decimal
    -0.06
     Decimal
    -0.06
    çIJĨæĢ§
    -0.06
    åħŃçĻ¾
    -0.06
    POSITIVE LOGITS
    ÒIJ
    0.09
    è¾ij
    0.08
    åıĹ访
    0.08
    odies
    0.07
    aires
    0.07
     %[
    0.07
    дай
    0.07
    chetta
    0.07
    astra
    0.07
     libert
    0.07
    Activations Density 0.455%

    No Known Activations