© 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. 18138
    Prev
    Next
    INDEX
    Explanations

    eighteen months, afternoon classes, Vik karma

    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
     _______,
    -0.07
    æĥħåĨµåĴĮ
    -0.07
    æī«çłģåħ³æ³¨
    -0.06
    assic
    -0.06
    åıĺåĮĸåĴĮ
    -0.06
    æĥħåĨµåIJİ
    -0.06
    descr
    -0.06
    acken
    -0.05
    两边
    -0.05
     Muj
    -0.05
    POSITIVE LOGITS
     zaÅĽ
    0.11
    åij¢
    0.09
     pedig
    0.09
     daraus
    0.09
    çļĦä¸ĢåĪĩéĥ½
    0.09
     же
    0.09
    çļĦäººä¹Ł
    0.09
     hingegen
    0.09
     thereafter
    0.08
     íĽĦìĹIJëĬĶ
    0.08
    Activations Density 0.310%

    No Known Activations