© 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. 3912
    Prev
    Next
    INDEX
    Explanations

    geometry and math topics

    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
    çĶ¨æĸĻ
    -0.09
    è¾ħæĸĻ
    -0.08
    JECTION
    -0.07
    顺åı£
    -0.07
    大åĿĹ
    -0.07
     Thảo
    -0.07
    stech
    -0.07
    åĪĩåħ¥
    -0.06
    åħ½
    -0.06
    éľĢè¦ģçļĦ
    -0.06
    POSITIVE LOGITS
     Killing
    0.08
    èĶ¬
    0.07
     sej
    0.07
     веÑĩ
    0.07
    ripp
    0.07
    åĨ»ç»ĵ
    0.07
    åľº
    0.07
    åı¯æĥľ
    0.07
     Posted
    0.07
    vest
    0.07
    Activations Density 0.002%

    No Known Activations