© 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. 48124
    Prev
    Next
    INDEX
    Explanations

    longer, closing, chapter

    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
    ...).
    -0.08
    ...,
    -0.07
    hen
    -0.07
    ,[],
    -0.07
    ikan
    -0.06
     ""),
    -0.06
    auta
    -0.06
    ãģ¨ãģĦãģĨãĤĪãģĨãģª
    -0.06
    åĪĨåĪ«ä¸İ
    -0.06
    ham
    -0.06
    POSITIVE LOGITS
    /rfc
    0.08
    icast
    0.08
    uage
    0.08
    ezo
    0.08
    olk
    0.08
    nodoc
    0.08
    |"
    0.07
    "|
    0.07
    -begin
    0.07
    clide
    0.07
    Activations Density 0.001%

    No Known Activations