© 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. 63110
    Prev
    Next
    INDEX
    Explanations

    argument or arguing

    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
    ward
    -0.09
    perience
    -0.08
    ellaneous
    -0.08
    ëłµ
    -0.08
    çĦ¶å¤§
    -0.07
    вно
    -0.07
    chetti
    -0.07
    èĢĮä¸Ķè¿ĺæĺ¯
    -0.07
    reamble
    -0.07
    ¾
    -0.07
    POSITIVE LOGITS
    ative
    0.10
    atively
    0.09
    uably
    0.09
    esis
    0.08
     against
    0.08
    onaut
    0.08
    ext
    0.08
    ÑĥменÑĤ
    0.08
    ìŁģ
    0.08
    against
    0.08
    Activations Density 0.039%

    No Known Activations