© 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. 55998
    Prev
    Next
    INDEX
    Explanations

    punctuation and conjunctions

    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
    åı¦è¡ĮéĢļçŁ¥
    -0.09
    è§Ħå®ļçļĦåħ¶ä»ĸ
    -0.09
    æ¡¥éķĩ
    -0.08
    æľĢåIJİæĺ¯
    -0.08
     finally
    -0.08
    æīĢå±ŀåĪĨç±»
    -0.08
     infine
    -0.08
    ./.
    -0.08
     Finally
    -0.07
    åºĶäºĪ
    -0.07
    POSITIVE LOGITS
    åħ¶
    0.08
    ä½Ĩåħ¶
    0.07
    vet
    0.07
    æľ¬èº«å°±
    0.07
     przede
    0.07
    æĽ´éĩįè¦ģçļĦæĺ¯
    0.06
    æĮīçIJĨ
    0.06
     Its
    0.06
    ä½Ĩå®ĥ
    0.06
    its
    0.06
    Activations Density 0.146%

    No Known Activations