© 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. 2061
    Prev
    Next
    INDEX
    Explanations

    code identifiers and strings

    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
    ìĪŃ
    -0.08
    oro
    -0.08
    rhein
    -0.08
    _overlay
    -0.08
    æķ¬
    -0.08
    ymar
    -0.08
    voi
    -0.07
    çĸı
    -0.07
    maz
    -0.07
    éģ¥
    -0.07
    POSITIVE LOGITS
    åĴĮæŶéĹ´
    0.07
    éĽĦåİļ
    0.07
     Gru
    0.07
    licas
    0.06
    åĴĮæĵįä½ľ
    0.06
    ace
    0.06
    iki
    0.06
    åľ¨ç»Ļ
    0.06
    ç»Ŀåľ°
    0.06
    åĴĮä¸Ģ个
    0.06
    Activations Density 0.063%

    No Known Activations