© 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. 26050
    Prev
    Next
    INDEX
    Explanations

    guess it might

    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
    lov
    -0.07
    âĢ¦but
    -0.07
    ä½Ĩæĺ¯è¿Ļ
    -0.07
    irt
    -0.07
    ç¿ģ
    -0.06
    ãĤĦãģĭ
    -0.06
    odes
    -0.06
    ong
    -0.06
    èł
    -0.06
    以åıĬ缸åħ³
    -0.06
    POSITIVE LOGITS
    %X
    0.07
     final
    0.07
    ByExample
    0.07
     ä»ĬæĹ¥
    0.07
    áŀ¶áŀĻ
    0.07
     Fazit
    0.07
    STANCE
    0.07
    ë§ĪìłĢ
    0.07
    æĪijåĨ³å®ļ
    0.07
    ottom
    0.07
    Activations Density 0.009%

    No Known Activations