© 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. 14912
    Prev
    Next
    INDEX
    Explanations

    choice for

    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
    pil
    -0.07
     rempla
    -0.07
    пÑĢе
    -0.07
    ffects
    -0.07
    zien
    -0.07
    .keywords
    -0.07
    åħ¬å¼Ģå¼ĢåºŃ
    -0.07
    =logging
    -0.07
    çľŁå¥½
    -0.07
     exclusive
    -0.07
    POSITIVE LOGITS
     answer
    0.08
     simply
    0.08
     unless
    0.08
    æľĢç®ĢåįķçļĦ
    0.08
     simple
    0.08
    çŃĶæ¡Ī
    0.08
     Simply
    0.07
     Unless
    0.07
     answered
    0.07
    ych
    0.07
    Activations Density 0.034%

    No Known Activations