© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 56853
    Prev
    Next
    INDEX
    Explanations

    from ... to

    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
    æ¯ĶæĪij们
    -0.07
    åįĥåįĥ
    -0.07
    èģĶæľº
    -0.07
    edd
    -0.07
     olev
    -0.06
    onder
    -0.06
    è®¤çľŁå¼Ģå±ķ
    -0.06
    ce
    -0.06
    æĹłæĥħçļĦ
    -0.06
    ottes
    -0.06
    POSITIVE LOGITS
    å§ĭèĩ³
    0.11
    å§ĭèĩ³ç»Ī
    0.10
    åħĥåĪ°
    0.10
    åįĹèĩ³
    0.10
    æĹ¥åĪ°
    0.09
    é«ĺåĪĨåĪ°ä½İåĪĨ
    0.09
    åį³æĹ¥èµ·èĩ³
    0.09
    çĤ¹èĩ³
    0.09
    å¼ĢåĪ°
    0.09
    大åĪ°
    0.08
    Activations Density 0.059%

    No Known Activations