© 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. 58251
    Prev
    Next
    INDEX
    Explanations

    percentage change

    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
    opil
    -0.08
    ัà¹Īว
    -0.08
     Klos
    -0.08
    cks
    -0.08
    ÏģÏħ
    -0.08
     Kred
    -0.08
    empat
    -0.08
    åĦªåħĪ
    -0.08
    è¿Ľåĩº
    -0.08
    idente
    -0.07
    POSITIVE LOGITS
    åŁºæķ°
    0.08
    çĻ¾åĪĨæ¯Ķ
    0.07
     percentage
    0.07
    津津
    0.07
    çĻ¾åĪĨä¹ĭ
    0.07
    åįłæ¯Ķ
    0.07
     Percent
    0.07
     multiplier
    0.07
    çĻ¾åĢį
    0.07
     sales
    0.06
    Activations Density 0.003%

    No Known Activations