© 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. 25273
    Prev
    Next
    INDEX
    Explanations

    options and methods

    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
     (
    -0.08
    -0.07
     (?
    -0.06
    幸
    -0.06
     /
    -0.06
     (?)
    -0.06
     *
    -0.06
    ...
    -0.06
    ple
    -0.06
    elle
    -0.06
    POSITIVE LOGITS
     móc
    0.09
    ceo
    0.09
    åıĬåħ¶åºĶçĶ¨
    0.09
    angled
    0.09
    ä¸īéĥ¨æĽ²
    0.09
    etailed
    0.08
     Alfon
    0.08
    çĤ¹åIJİ
    0.08
    imed
    0.08
     disertai
    0.08
    Activations Density 0.027%

    No Known Activations