© 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. 29627
    Prev
    Next
    INDEX
    Explanations

    reports and contact information

    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
    è¿ijå¹³
    -0.09
    åĮºäººæ°ijæĶ¿åºľ
    -0.09
    åĪĿå¿ĥ使åij½
    -0.09
    åıijå¸ĥåħ¬åijĬ称
    -0.09
    ä»Ĭ天å°ıç¼ĸå°±
    -0.09
    æĪIJåĬŁåIJİåį³åı¯
    -0.08
    DidLoad
    -0.08
    éŁŃ
    -0.08
    å¼Ģæľį
    -0.08
    /MIT
    -0.08
    POSITIVE LOGITS
    æĬ½
    0.08
    xx
    0.07
    æĺ¯æĪij们çļĦ
    0.07
    åģļ为
    0.07
    æĺ¯æĪij
    0.07
    (xx
    0.06
    带
    0.06
    äºĮ次
    0.06
    åľ¨åݻ年
    0.06
    æŃ¤é¡¹
    0.06
    Activations Density 0.002%

    No Known Activations