© 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. 64477
    Prev
    Next
    INDEX
    Explanations

    personal interests and timelines

    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
     загÑĢ
    -0.08
    ÑĮÑİ
    -0.08
    orti
    -0.08
    Lat
    -0.07
    ä¿Ŀè¯ģäºĨ
    -0.07
    orial
    -0.07
     neoliber
    -0.07
     sucks
    -0.07
    низ
    -0.07
    quez
    -0.07
    POSITIVE LOGITS
     either
    0.07
    å°Ĩå®ĥ
    0.07
     Either
    0.06
    æĬĬå®ĥ
    0.06
    indow
    0.06
     en
    0.06
    æĬķèµĦæĪĸ
    0.06
    thouse
    0.06
    <|box_end|>
    0.06
     Wes
    0.06
    Activations Density 0.021%

    No Known Activations