© 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. 11451
    Prev
    Next
    INDEX
    Explanations

    headings, volume, league, step, stepper, mgr

    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
    -0.06
    anc
    -0.06
    ner
    -0.05
    8
    -0.05
    ans
    -0.05
    åķĨ
    -0.05
    .ph
    -0.05
    æĶ¶æķĽ
    -0.05
    elen
    -0.05
    oko
    -0.05
    POSITIVE LOGITS
     Grosso
    0.09
    ç±»çŃī
    0.09
    licherweise
    0.09
    æĹ¥æĸ°æľĪ
    0.08
    gespr
    0.08
    жÑĮ
    0.08
    ãģ®ãģĭãĤĤãģĹãĤĮ
    0.08
    æĸĩåĮĸä¼łæĴŃæľīéĻIJåħ¬åı¸
    0.08
    dbo
    0.08
    ithub
    0.08
    Activations Density 0.004%

    No Known Activations