© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 64022
    Prev
    Next
    INDEX
    Explanations

    time ago or since

    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
    ÙIJÙĩ
    -0.08
    å¾Ĺ天
    -0.08
    åľ¨å½ĵæŶ
    -0.08
    å½ĵ天ä¸ĭåįĪ
    -0.08
    ä¸Ģå¤ķ
    -0.07
    iglich
    -0.07
    å½ĵæŶ
    -0.07
    ocio
    -0.07
    å¾Ģ常ä¸Ģæł·
    -0.07
    æķĻèĤ²åıijå±ķ
    -0.07
    POSITIVE LOGITS
    å·²ç»ıè¶ħè¿ĩ
    0.11
     yet
    0.10
    çŁ£
    0.10
    äºĨåIJ§
    0.10
    å·²è¿ĩ
    0.10
    çļĦ人äºĨ
    0.09
    äºĨåķĬ
    0.09
    å·²ç»ıæĺ¯
    0.09
    å·²è¶ħè¿ĩ
    0.09
    å·²ç»ıåĪ°äºĨ
    0.09
    Activations Density 0.384%

    No Known Activations