© 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. 10109
    Prev
    Next
    INDEX
    Explanations

    symbols and abbreviations definitions

    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
     cum
    -0.06
    éĽĨ
    -0.06
    å¤Ħå¤Ħ
    -0.06
    羣
    -0.06
    ↵↵
    -0.05
    åħħ满äºĨ
    -0.05
    als
    -0.05
     Levy
    -0.05
    plete
    -0.05
    cus
    -0.05
    POSITIVE LOGITS
    à¯įவ
    0.08
     âĤ¬*
    0.08
    è¢
    0.08
     enough
    0.08
    adero
    0.08
     rahas
    0.08
    populate
    0.08
    NESS
    0.07
    vaard
    0.07
     **:**
    0.07
    Activations Density 0.009%

    No Known Activations