© 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. 28411
    Prev
    Next
    INDEX
    Explanations

    collecting, accumulating, bag, list

    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
    lisi
    -0.08
    åºĶå½ĵæĮīçħ§
    -0.08
    ulg
    -0.07
    inari
    -0.07
     Hurt
    -0.07
    sene
    -0.07
     sire
    -0.07
    è¯įåħ¸
    -0.07
    èĶ¼
    -0.07
    illos
    -0.07
    POSITIVE LOGITS
    æĶ¶éĽĨ
    0.11
     accum
    0.11
     accumulate
    0.10
     collecting
    0.10
     accumulation
    0.10
     Accum
    0.10
    è®°ä¸ĭ
    0.10
     collect
    0.10
    accum
    0.10
     accumulating
    0.10
    Activations Density 0.056%

    No Known Activations