© 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. 55620
    Prev
    Next
    INDEX
    Explanations

    strip out or remove

    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
    avings
    -0.06
    ATHER
    -0.06
    -0.06
     اÙĦØŃد
    -0.06
    çĻ¾èįī
    -0.06
     somebody
    -0.06
     toned
    -0.06
    æĤ¨çļĦä½įç½®
    -0.06
    ashire
    -0.06
     likewise
    -0.06
    POSITIVE LOGITS
     лиÑĪ
    0.09
    ä¸įå¿ħè¦ģ
    0.08
    ä¸įå¿ħè¦ģçļĦ
    0.08
    alp
    0.08
     unnecessary
    0.08
     undue
    0.08
     obvious
    0.08
    æĢĿèŃ°
    0.08
     лиÑĪниÑħ
    0.08
    顾ä¹ĭ忧
    0.07
    Activations Density 0.050%

    No Known Activations