© 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. 41891
    Prev
    Next
    INDEX
    Explanations

    attribution after quote

    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
    èĢĮéĻį
    -0.07
    fell
    -0.06
     Ðĵо
    -0.06
    æī©å±ķèµĦæĸĻ
    -0.06
    னà¯įப
    -0.06
    .ByteArray
    -0.06
    并为
    -0.06
    awl
    -0.06
    çī¡
    -0.06
    å±ķå¼Ģåħ¨æĸĩ
    -0.06
    POSITIVE LOGITS
     ìĭ¤
    0.08
     said
    0.08
    said
    0.08
    edar
    0.08
    ç¨Ģæľī
    0.07
    说åĪ°è¿ĻéĩĮ
    0.07
    æµ·é»ĺ
    0.07
    rus
    0.07
    empre
    0.07
    chal
    0.07
    Activations Density 0.089%

    No Known Activations