© 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. 4321
    Prev
    Next
    INDEX
    Explanations

    going without worry

    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
    auer
    -0.07
    天æĪIJ
    -0.07
    åIJĮæĹ¶ä¹Ł
    -0.07
    oard
    -0.07
    å·²æĪIJ
    -0.07
    èĤ©è´Ł
    -0.07
    åĮĹè¾°
    -0.06
    egel
    -0.06
    uce
    -0.06
    è´¢æºIJ
    -0.06
    POSITIVE LOGITS
    è¾ĸ
    0.08
    anton
    0.07
    enni
    0.07
    åIJ«
    0.07
    æĽ²çº¿
    0.07
    —even
    0.07
    appa
    0.06
    _BAR
    0.06
    ffi
    0.06
    çªĹå¸ĺ
    0.06
    Activations Density 0.015%

    No Known Activations