© 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. 46424
    Prev
    Next
    INDEX
    Explanations

    asking questions

    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
    aeda
    -0.07
    ymar
    -0.07
    _minus
    -0.07
    _probs
    -0.07
    ovin
    -0.07
    etch
    -0.07
    alina
    -0.06
    jera
    -0.06
    ä¸ĢæŦ
    -0.06
    ersch
    -0.06
    POSITIVE LOGITS
    /how
    0.08
    ä¸ĢéĹ®
    0.08
     ÙĪÙĥÙĬÙģ
    0.08
    éĹ®
    0.08
    以åıĬå¦Ĥä½ķ
    0.08
    quires
    0.08
    åķı
    0.07
    åķıãģĦ
    0.07
     questions
    0.07
    ä¼łä¸ĸ
    0.07
    Activations Density 0.128%

    No Known Activations