© 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. 1146
    Prev
    Next
    INDEX
    Explanations

    asking for help or a solution

    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
    主è¦ģçĶ±
    -0.07
    å¿ħé¡»çĶ±
    -0.06
    è§Ħå®ļçļĦåħ¶ä»ĸ
    -0.06
    ãģĹãģĿãģĨ
    -0.06
    åį´åĽłä¸º
    -0.06
    ä½Ĩ并ä¸į
    -0.06
    æĺİæĺİæĺ¯
    -0.06
    èĢĮä¸Ķæĺ¯
    -0.06
    æĩĤçļĦ
    -0.06
    owi
    -0.06
    POSITIVE LOGITS
    å°±åı¯ä»¥äºĨ
    0.15
    ä¸ºå®ľ
    0.12
    åį³åı¯
    0.12
    æľĢåIJĪéĢĤ
    0.11
    å°±è¡ĮäºĨ
    0.11
     suffice
    0.11
    å°±å¤ŁäºĨ
    0.11
    ")==
    0.11
    å°±è¡Į
    0.11
    è°ģéĥ½
    0.10
    Activations Density 0.114%

    No Known Activations