© 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. 49195
    Prev
    Next
    INDEX
    Explanations

    alternatives or options

    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
    æĬķèµĦæĪĸ
    -0.08
    å·¥ä½ľæĪĸ
    -0.08
    ekin
    -0.07
    iciones
    -0.07
    roud
    -0.07
    elius
    -0.07
    æī®æ¼Ķ
    -0.07
    leet
    -0.07
    áros
    -0.07
    rray
    -0.06
    POSITIVE LOGITS
     alternatively
    0.11
    ignal
    0.09
     alternativ
    0.08
     perhaps
    0.08
     simply
    0.08
    å¹²èĦĨ
    0.08
    ç´¢æĢ§
    0.08
     mož
    0.08
     atleast
    0.07
     же
    0.07
    Activations Density 0.225%

    No Known Activations