© 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. 60523
    Prev
    Next
    INDEX
    Explanations

    doesn't work

    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
     likewise
    -0.09
    urna
    -0.09
    ulação
    -0.08
     modest
    -0.08
    вÑĸ
    -0.08
    så
    -0.07
    æĦĪåĬł
    -0.07
     seldom
    -0.07
    ý
    -0.07
    μη
    -0.07
    POSITIVE LOGITS
     things
    0.07
     thing
    0.07
    å¸ĮæľĽèĥ½å¤Łå¸®åĬ©
    0.07
    éķ¿çĿĢ
    0.07
     lang
    0.06
    è¿Ļ个äºĭæĥħ
    0.06
    enan
    0.06
    -looking
    0.06
    å²ģçļĦæŶåĢĻ
    0.06
     |(
    0.06
    Activations Density 0.009%

    No Known Activations