© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 22905
    Prev
    Next
    INDEX
    Explanations

    suffices, controls, filtration, efficac, predomin

    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
    anger
    -0.07
    èĢĮä¸įæĺ¯
    -0.07
    ä¸įæıIJ
    -0.06
    楷
    -0.06
    auer
    -0.06
    æ·±åĪ»é¢Ĩä¼ļ
    -0.06
     flashed
    -0.06
    гей
    -0.06
    oment
    -0.06
    çīĩ
    -0.05
    POSITIVE LOGITS
    åĪĻæĺ¯
    0.14
    åīĩæĺ¯
    0.12
    åĪĻå°Ĩ
    0.11
    åĪĻ
    0.11
     hingegen
    0.10
    åĪĻä¼ļ
    0.10
    åĪĻéľĢè¦ģ
    0.10
    åĪĻ为
    0.10
    åĪĻæľī
    0.10
    åĪĻåľ¨
    0.10
    Activations Density 0.040%

    No Known Activations