© 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. 41903
    Prev
    Next
    INDEX
    Explanations

    code syntax: .shift, requires, +

    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
    orro
    -0.08
    iy
    -0.07
    ×Ļ×Ķ
    -0.06
    تÙĥ
    -0.06
    åħ¶å¯¹
    -0.06
    _typ
    -0.06
    ä¸Ģ楼
    -0.06
    ç¯Ħ
    -0.06
    åħħåĪĨåıijæĮ¥
    -0.06
    å¹´éĩĮ
    -0.06
    POSITIVE LOGITS
    ä¸įæķ¢çĽ¸ä¿¡
    0.08
    á»įng
    0.07
    è·³
    0.07
    ANC
    0.07
    å®īå¹³
    0.07
     skip
    0.07
    zey
    0.07
    interop
    0.07
    &display
    0.07
    -bind
    0.06
    Activations Density 0.002%

    No Known Activations