© 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. 63719
    Prev
    Next
    INDEX
    Explanations

    two or both

    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
    leston
    -0.09
    ëģĶ
    -0.09
    eki
    -0.08
    avu
    -0.08
    laš
    -0.08
    ä¸Ģ鸣
    -0.08
    çĻ¾å·Ŀ
    -0.08
    æį¢ä»£
    -0.08
    uera
    -0.08
    andia
    -0.08
    POSITIVE LOGITS
    -thirds
    0.13
     mÆ°Æ¡i
    0.11
    (li
    0.09
    -dimensional
    0.09
    æĪĸ以ä¸Ĭ
    0.09
     sexes
    0.09
    åĪĨåĪ«æĺ¯
    0.08
    æĬŀ
    0.08
    ä¸Ģ个æĺ¯
    0.08
    ÑģÑĤоÑĢон
    0.08
    Activations Density 0.002%

    No Known Activations