© 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. 7383
    Prev
    Next
    INDEX
    Explanations

    analysis and percentages

    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
    صات
    -0.08
    gå
    -0.08
    *</
    -0.08
     numbered
    -0.08
    åħ¬çĪµ
    -0.08
    çĶ³è¯·æī§è¡Į
    -0.08
    计æķ°åĻ¨
    -0.08
    ãĤĴãĤ¹ãĥĪãĥĥãĤ¯
    -0.08
    éĴ§
    -0.07
    ÙĨÛĮÙĨ
    -0.07
    POSITIVE LOGITS
    åįłæ¯Ķ
    0.08
     percentages
    0.07
     elemental
    0.07
    çĻ¾åĪĨæ¯Ķ
    0.07
    percentage
    0.07
    æ¯Ķä¾ĭ
    0.07
     ratio
    0.07
     percentage
    0.07
    component
    0.07
     Component
    0.07
    Activations Density 0.004%

    No Known Activations