© 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. 22758
    Prev
    Next
    INDEX
    Explanations

    dosage per weight

    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
    åĴĮåŁ¹åħ»
    -0.08
    amat
    -0.07
    æ±Ĥæĺ¯
    -0.07
    pat
    -0.07
    FromArray
    -0.07
     дÑĥÑħ
    -0.07
    øj
    -0.07
    ÙĪدÙĬØ©
    -0.07
    (/^\
    -0.07
    åľĨ
    -0.07
    POSITIVE LOGITS
    åĩĮ
    0.07
    è¶ħä½İ
    0.07
    chtig
    0.07
     surfaces
    0.06
    å«Ĥ
    0.06
     susc
    0.06
     ÙħساØŃØ©
    0.06
    idget
    0.06
    æľīåģ¿
    0.06
    gett
    0.06
    Activations Density 0.034%

    No Known Activations