© 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. 8046
    Prev
    Next
    INDEX
    Explanations

    former, buck, honesty, throw, underscores

    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
    steen
    -0.08
    æīįæĺ¯çľŁæŃ£çļĦ
    -0.07
    доне
    -0.07
     wÅĤaÅĽnie
    -0.07
    åįıåķĨä¸Ģèĩ´
    -0.07
    è¿ĻæŃ£æĺ¯
    -0.07
    åħĥéĴ±
    -0.06
    _FINE
    -0.06
    gary
    -0.06
    atan
    -0.06
    POSITIVE LOGITS
     irrelevant
    0.10
     unrelated
    0.09
    ä¸įåIJĪ
    0.09
    æĺ¯ä¸įåı¯èĥ½
    0.09
    æĹłåħ³
    0.09
    ä¸įåħ·å¤ĩ
    0.09
    æĺ¯æĹłæ³ķ
    0.08
     unrealistic
    0.08
    ä¸įåı¯èĥ½
    0.08
    æĹłæķĪ
    0.08
    Activations Density 0.001%

    No Known Activations