© 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. 34492
    Prev
    Next
    INDEX
    Explanations

    apply multiple filters

    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
    åĩºæģ¯
    -0.10
    .parseFloat
    -0.09
    वल
    -0.09
    åħ®åħ®
    -0.09
    çİ©æĦı
    -0.09
    ification
    -0.09
    waard
    -0.09
    uage
    -0.08
    ecu
    -0.08
    çİ©æĦıåĦ¿
    -0.08
    POSITIVE LOGITS
    ments
    0.09
    OrElse
    0.09
    /octet
    0.08
    åĪ°çļĦ
    0.08
    èĢIJå¾·
    0.08
    arently
    0.07
    lying
    0.07
    æ¸Īãģ¿
    0.07
    à¸ŀลิà¹Ģà¸Ħ
    0.07
    _ONCE
    0.07
    Activations Density 0.101%

    No Known Activations