© 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. 30312
    Prev
    Next
    INDEX
    Explanations

    positivity/negativity

    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
    abl
    -0.08
     astounding
    -0.07
    æį¶
    -0.07
     optimum
    -0.07
    amage
    -0.07
     Beaver
    -0.07
    ä¼ĺæĥł
    -0.07
    ä¸įäºĨäºĨ
    -0.07
    phin
    -0.07
    羣æĺ¯å¤ª
    -0.07
    POSITIVE LOGITS
     positive
    0.15
    positive
    0.14
     positivity
    0.13
    Positive
    0.13
     Positive
    0.13
    -positive
    0.13
    æŃ£çļĦ
    0.13
     negativity
    0.13
    _positive
    0.12
    è´ŁçļĦ
    0.12
    Activations Density 0.010%

    No Known Activations