© 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. 45342
    Prev
    Next
    INDEX
    Explanations

    recommend

    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
     вовÑĢемÑı
    -0.07
    åľ¨æŃ¤æ¬¡
    -0.07
    ä¸įæĺ¯åĽłä¸º
    -0.07
    çĥ¯
    -0.07
    第äºĮ大
    -0.07
    ä»ħæѤ
    -0.06
    çŁŃçŁŃ
    -0.06
    èµ·åĽł
    -0.06
     pleasure
    -0.06
    å®ĥæīĢ
    -0.06
    POSITIVE LOGITS
     methods
    0.11
    çļĦæĸ¹æ³ķæĺ¯
    0.11
    methods
    0.11
    åı¯è¡ĮçļĦ
    0.10
    çļĦæĸ¹æ³ķ
    0.10
    åı¯ä»¥éĩĩçĶ¨
    0.10
    åı¯éĩĩçĶ¨
    0.10
    以ä¸ĭæŃ¥éª¤
    0.10
    æĸ¹æ³ķæĺ¯
    0.09
    çļĦåĬŀæ³ķ
    0.09
    Activations Density 0.133%

    No Known Activations