© 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. 10037
    Prev
    Next
    INDEX
    Explanations

    monotonic functions and slopes

    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
    åį³çĶ¨
    -0.08
    иÑģи
    -0.08
    ubil
    -0.08
     éché
    -0.08
    TURE
    -0.07
    åħ»
    -0.07
    ubl
    -0.07
    å°ĺ
    -0.07
    足ä¸įåĩºæĪ·
    -0.07
    åij¨åĽĽ
    -0.07
    POSITIVE LOGITS
     monot
    0.15
    åįķè°ĥ
    0.13
     slope
    0.10
    Interval
    0.09
     Slo
    0.09
     continuous
    0.08
     slopes
    0.08
    åľ¨æķ´ä¸ª
    0.08
    slope
    0.08
     Lips
    0.08
    Activations Density 0.004%

    No Known Activations