© 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. 58040
    Prev
    Next
    INDEX
    Explanations

    expected

    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
    ê¹IJ
    -0.09
    ìį¨
    -0.08
    éļĪ
    -0.08
    pike
    -0.08
    icular
    -0.07
    anship
    -0.07
    олÑĮ
    -0.07
    ETHOD
    -0.07
    otin
    -0.07
    pery
    -0.07
    POSITIVE LOGITS
    å·²ä¹ħçļĦ
    0.10
    à¸ģารà¸ĵà¹Į
    0.10
    éĢļãĤĬãģ®
    0.09
    orate
    0.08
    éĢļãĤĬãģ«
    0.08
    roll
    0.08
    entially
    0.08
    ancies
    0.07
     Äijợi
    0.07
    åĪ°çļĦ
    0.07
    Activations Density 0.037%

    No Known Activations