© 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. 39235
    Prev
    Next
    INDEX
    Explanations

    however, a contrast marker

    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
     tamp
    -0.08
    å½ĵçĦ¶æĺ¯
    -0.07
     indeed
    -0.07
     certes
    -0.07
     zaten
    -0.07
    æľ¬å°±æĺ¯
    -0.06
    æŀľçĦ¶
    -0.06
    æŀľçĦ¶æĺ¯
    -0.06
    ients
    -0.06
     assur
    -0.06
    POSITIVE LOGITS
    åį´
    0.10
    åį´è®©
    0.09
    ä»ĸåį´
    0.09
    åį´ä¸įèĥ½
    0.09
    ä½łåį´
    0.09
    åį´åĽłä¸º
    0.09
     notwithstanding
    0.08
    æĪijåį´
    0.08
    ä¾ĭå¤ĸ
    0.08
    åı¦ä¸Ģæĸ¹éĿ¢
    0.08
    Activations Density 0.374%

    No Known Activations