© 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. 57421
    Prev
    Next
    INDEX
    Explanations

    miles

    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
    åģļ为
    -0.08
    UC
    -0.07
    IfExists
    -0.07
    åħ¨æĸĩéĺħ读
    -0.07
    os
    -0.07
     Ive
    -0.06
     hell
    -0.06
    lo
    -0.06
    ละ
    -0.06
    ukse
    -0.06
    POSITIVE LOGITS
    ighton
    0.08
    åĩºå¥ĩ
    0.08
    /rfc
    0.08
    æľĢéĩįè¦ģçļĦæĺ¯
    0.07
    arti
    0.07
    éĶ»
    0.07
     bref
    0.07
    uris
    0.07
    revet
    0.07
    ABCDE
    0.06
    Activations Density 0.075%

    No Known Activations