© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 64064
    Prev
    Next
    INDEX
    Explanations

    order or position

    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
    aves
    -0.07
    _based
    -0.07
    æķħæѤ
    -0.07
    çĮ¬
    -0.06
    让è¿ĻäºĽ
    -0.06
    áĥ£áĥľ
    -0.06
    ovi
    -0.06
    heim
    -0.06
    áĢ¯
    -0.06
    ä¹Łæľªå¿ħ
    -0.06
    POSITIVE LOGITS
    lj
    0.07
    ungan
    0.07
    ðŁĺī
    0.06
    æĿ¥åºĹ
    0.06
    TRL
    0.06
    λικ
    0.06
    AxisSize
    0.06
     oef
    0.06
    MemoryWarning
    0.06
    ãģĭãĤĮ
    0.06
    Activations Density 0.042%

    No Known Activations