© 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. 27190
    Prev
    Next
    INDEX
    Explanations

    stick with, just share, 'll share

    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
    mpl
    -0.06
    çĶļèĩ³è¿ĺæľī
    -0.06
    onen
    -0.06
    ler
    -0.06
    æ
    -0.06
    elled
    -0.06
    è¯ł
    -0.06
    æ¯Ķ
    -0.06
    ä¸ĢèĦī
    -0.06
    诧
    -0.06
    POSITIVE LOGITS
    ãģ¨ãĤĬãģĤãģĪãģļ
    0.08
    ä¸į管
    0.08
    å§ij
    0.08
    ä¸įè¡ĮäºĨ
    0.08
    ä¸į管æĢİæł·
    0.08
    Despite
    0.08
    å°±å½ĵ
    0.08
    à¸ļà¸Ńล
    0.08
    æĮīåħ¶
    0.08
    æľĢ常è§ģçļĦ
    0.08
    Activations Density 0.016%

    No Known Activations