© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 51927
    Prev
    Next
    INDEX
    Explanations

    definition

    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
    cier
    -0.08
    }):
    -0.08
    åĪĻä¼ļ
    -0.07
    ä¿¡æģ¯ç½ij绾
    -0.07
    oplast
    -0.07
    çĦ¶å¤§
    -0.07
    çĥ¨
    -0.07
    å®ŀéĻħéľĢè¦ģ
    -0.07
    åĪĻéľĢè¦ģ
    -0.07
    çŃīåħ¶ä»ĸ
    -0.07
    POSITIVE LOGITS
    å®ĥçļĦ
    0.09
    å®ĥ
    0.09
     ì£¼ë¡ľ
    0.09
    å®ĥæľī
    0.09
    å®ĥåı¯ä»¥
    0.09
    å®ĥæĺ¯
    0.09
    å®ĥ以
    0.09
    å®ĥåľ¨
    0.08
    ç®ĢåįķæĿ¥è¯´
    0.08
    å®ĥèĥ½å¤Ł
    0.08
    Activations Density 0.220%

    No Known Activations