© 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. 15070
    Prev
    Next
    INDEX
    Explanations

    treatment and efficacy

    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
    åİŁå§ĭçļĦ
    -0.08
    href
    -0.08
    ripper
    -0.08
    æĪIJæŀľ
    -0.07
    unami
    -0.07
    kunde
    -0.07
    åİŁå§ĭ
    -0.07
     Donate
    -0.07
    åĩºéĿ¢
    -0.07
    æĿ
    -0.07
    POSITIVE LOGITS
    æľ¬åĵģ
    0.11
    azor
    0.07
     impairment
    0.07
    ä¸Ĭå¸Ĥ
    0.07
     product
    0.07
    ä¸Ĭå¸ĤåIJİ
    0.06
    å¯Ĥå¯ŀ
    0.06
    oss
    0.06
     pursuant
    0.06
    attro
    0.06
    Activations Density 0.321%

    No Known Activations