© 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. 55303
    Prev
    Next
    INDEX
    Explanations

    omega-6, gastric, dwarf, canon, member, brute, miliary

    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
    hang
    -0.08
    ×ķף
    -0.07
    _GO
    -0.07
    imy
    -0.07
    çļĦéĤ£äºĽ
    -0.07
    åIJĦè¡Į
    -0.07
    åħ·ä½ĵæݪæĸ½
    -0.07
    ÑģÑĸв
    -0.06
    å°±æĺ¯æĪijçļĦ
    -0.06
    èĢĮå¤į
    -0.06
    POSITIVE LOGITS
    å½ĵä¹ĭæĹłæĦ§
    0.09
    åIJįåī¯åħ¶å®ŀçļĦ
    0.08
     Type
    0.08
    ç±»åŀĭçļĦ
    0.08
    åIJįåī¯åħ¶å®ŀ
    0.08
    à¸Ľà¸£à¸°à¹Ģà¸łà¸Ĺ
    0.08
    ãĤ¿ãĤ¤ãĥĹãģ®
    0.08
    æĦıä¹īä¸ĬçļĦ
    0.08
    ç±»åŀĭ
    0.08
    ç±»åŀĭ为
    0.08
    Activations Density 0.048%

    No Known Activations