© 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. 39006
    Prev
    Next
    INDEX
    Explanations

    followed by articles or determiners

    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
     ìĹĨì§Ģë§Į
    -0.09
    à¸ĵะ
    -0.08
    opter
    -0.08
     schlim
    -0.08
     tellement
    -0.08
    무리
    -0.07
    ihak
    -0.07
    ajor
    -0.07
     ìĹĨê³ł
    -0.07
    çī¹åĪ«æĺ¯
    -0.07
    POSITIVE LOGITS
    atto
    0.07
    åıĻ
    0.06
    ché
    0.06
    ç¾ģ
    0.06
    dan
    0.06
     ÙĪاÙĦØ°ÙĬ
    0.06
    äºĨåĩºæĿ¥
    0.06
    Âł
    0.05
    ÅĽmy
    0.05
    çŃīçŃī
    0.05
    Activations Density 1.169%

    No Known Activations