© 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. 41337
    Prev
    Next
    INDEX
    Explanations

    unless followed by an exception

    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
    å¾Īåı¯èĥ½æĺ¯
    -0.09
    atap
    -0.08
    å¾Īåı¯èĥ½
    -0.08
    以åıĬä¸İ
    -0.08
    Pub
    -0.08
    ocat
    -0.08
    为åIJĮåѦ们
    -0.07
    often
    -0.07
    probably
    -0.07
    çīĪæĿĥå½ĴåİŁä½ľèĢħæīĢæľī
    -0.07
    POSITIVE LOGITS
    æľīåĪ«
    0.09
     اÛĮÙĨÚ©Ùĩ
    0.09
    æľīçī¹æ®Ĭ
    0.08
    æľīåħ¶ä»ĸ
    0.08
    çī¹åĪ«è¯´æĺİ
    0.07
    ä¹İ
    0.07
    以任ä½ķ
    0.07
    å·§åIJĪ
    0.07
    强迫
    0.07
    !!,
    0.07
    Activations Density 0.021%

    No Known Activations