© 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. 56719
    Prev
    Next
    INDEX
    Explanations

    numerical values and ordinary pigs

    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
    klass
    -0.07
    essler
    -0.07
    explo
    -0.07
    ÙĪاØŃ
    -0.07
    åĹ£
    -0.07
    载客
    -0.07
    /org
    -0.07
    éģ
    -0.07
     unheard
    -0.06
    cuit
    -0.06
    POSITIVE LOGITS
    uen
    0.07
    夯
    0.07
     Behaviour
    0.07
    å²ij
    0.07
    天ä¸ĭ第ä¸Ģ
    0.06
     evaluating
    0.06
     Behavior
    0.06
    ìłĢ
    0.06
    uess
    0.06
     wart
    0.06
    Activations Density 0.004%

    No Known Activations