© 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. 10376
    Prev
    Next
    INDEX
    Explanations

    official reports and details

    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
    <|box_end|>
    -0.06
    č↵
    -0.06
    ase
    -0.06
    sort
    -0.06
    çijķ
    -0.06
     sort
    -0.06
    č↵č↵
    -0.06
    æ·³
    -0.05
     č↵
    -0.05
    çĶļèĢħ
    -0.05
    POSITIVE LOGITS
    ë¥
    0.07
    esty
    0.07
    íľĺ
    0.07
    uver
    0.07
    elpers
    0.07
    losure
    0.07
    irit
    0.07
    리íķľ
    0.07
    éķ¿ç©º
    0.06
    ëĤĻ
    0.06
    Activations Density 0.259%

    No Known Activations