© 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. 24930
    Prev
    Next
    INDEX
    Explanations

    prepared for analysis

    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
    ichel
    -0.07
    åľ¨æī§è¡Į
    -0.07
    éĶ¦
    -0.07
    ä¸įèĥ½è®©
    -0.07
     subconscious
    -0.07
     ÑĥказÑĭ
    -0.07
    ç®Ĺ
    -0.07
    就让
    -0.07
    urning
    -0.07
    容å¿į
    -0.07
    POSITIVE LOGITS
    å¿ħè¦ģçļĦ
    0.08
    以å¤ĩ
    0.08
    å¿ħè¦ģæŶ
    0.08
    æĪĸ缴æİ¥
    0.07
     ëĭ¤ìĭľ
    0.07
    åĨįè¿Ľè¡Į
    0.07
    åĬłåĭĴ
    0.07
    å¿ħè¦ģ
    0.07
     further
    0.07
     optionally
    0.07
    Activations Density 0.090%

    No Known Activations