© 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. 58507
    Prev
    Next
    INDEX
    Explanations

    details and distinctions

    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
    Ñĥго
    -0.09
    astique
    -0.08
    loff
    -0.08
    åį´ä¸įæĺ¯
    -0.08
    å°Ķé¡¿
    -0.08
    xAB
    -0.08
    lát
    -0.07
    ä¸įæĺ¯ä¸ºäºĨ
    -0.07
    ienst
    -0.07
    å·¥ä½ľéľĢè¦ģ
    -0.07
    POSITIVE LOGITS
     explicitly
    0.08
    åħ·ä½ĵ
    0.08
    åħ·ä½ĵçļĦ
    0.08
    explicit
    0.08
     explicit
    0.07
    åħ·ä½ĵçļĦãģ«
    0.07
    æĹ¢çĦ¶æĺ¯
    0.07
     specifics
    0.07
    æľĢèµ·çłģ
    0.07
    åºĶæľīçļĦ
    0.07
    Activations Density 0.083%

    No Known Activations