© 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. 56804
    Prev
    Next
    INDEX
    Explanations

    like it, kind of, regardless of

    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
     infatti
    -0.07
    enso
    -0.07
    并æĮīçħ§
    -0.07
    aliste
    -0.07
    elok
    -0.06
    éal
    -0.06
    ategorical
    -0.06
     обаÑĩе
    -0.06
    俯åį§
    -0.06
    ervis
    -0.06
    POSITIVE LOGITS
     appunto
    0.09
     usw
    0.07
     etc
    0.07
    ä¸ĢåĽŀäºĭ
    0.07
    ä¸ĭåIJĮ
    0.07
    å°±è¡Į
    0.07
    éĩıèĥ½
    0.07
    oug
    0.07
    åıĪåĥı
    0.07
     somehow
    0.07
    Activations Density 0.010%

    No Known Activations