© 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. 19596
    Prev
    Next
    INDEX
    Explanations

    nanoparticles and particles

    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
     Inputs
    -0.08
     inputs
    -0.08
     Kenn
    -0.07
    Inputs
    -0.07
     conventions
    -0.07
    æ¦Ĥ
    -0.07
     input
    -0.07
     durations
    -0.06
    èĩŃæ°§
    -0.06
    è¾ĵåħ¥
    -0.06
    POSITIVE LOGITS
    åĪĨå¸ĥ
    0.09
    å½¢æĪIJçļĦ
    0.09
    anch
    0.08
    å½¢æĪIJäºĨ
    0.08
     formed
    0.08
     daģı
    0.08
     redistributed
    0.08
    åĪĨå¸ĥäºİ
    0.08
    åĪĨå¸ĥåľ¨
    0.08
     layer
    0.08
    Activations Density 0.022%

    No Known Activations