© 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. 65334
    Prev
    Next
    INDEX
    Explanations

    ventricular anteversion polarity

    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
    immel
    -0.08
    имо
    -0.07
    itale
    -0.07
    ارÙĩ
    -0.07
     invariably
    -0.07
    اÙĨد
    -0.07
    ë³µ
    -0.07
    çĹħæ¯ĴæĦŁæŁĵ
    -0.07
     converged
    -0.06
    kie
    -0.06
    POSITIVE LOGITS
    _hashes
    0.07
    earn
    0.07
    ึà¸ĩ
    0.07
    ä¹ĭæ¯Ķ
    0.06
    /message
    0.06
    åĪ«çļĦ
    0.06
     ...
    0.06
    åĪ«åIJį
    0.06
    ious
    0.06
    客æłĪ
    0.06
    Activations Density 0.058%

    No Known Activations