© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2380
    Prev
    Next
    INDEX
    Explanations

    explanation and understanding

    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
    ecker
    -0.08
     TER
    -0.07
    viet
    -0.07
    ä¸ĸå¤ĸ
    -0.07
    æīĵæ°´
    -0.06
    nbr
    -0.06
    comma
    -0.06
    åĪ©å¤ļ
    -0.06
    人çĶŁä¸Ń
    -0.06
    ynek
    -0.06
    POSITIVE LOGITS
     underlying
    0.11
     explanations
    0.11
     reasoning
    0.10
    èĢĮä¸įæĺ¯
    0.10
    ç´įå¾Ĺ
    0.10
    why
    0.10
     rather
    0.09
     WHY
    0.09
    èĥĮåIJİçļĦ
    0.09
     behind
    0.09
    Activations Density 0.090%

    No Known Activations