© 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. 42339
    Prev
    Next
    INDEX
    Explanations

    unpublished legal opinions

    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
    pera
    -0.08
    PageIndex
    -0.08
    åĩłä¹İæīĢæľī
    -0.07
    å¹²åĺĽ
    -0.07
    äºĶèĬ±åħ«
    -0.07
    ål
    -0.07
    ewa
    -0.07
    ÑĪенÑĮ
    -0.07
    Ñģами
    -0.07
    iak
    -0.07
    POSITIVE LOGITS
    ä¸įåĽł
    0.07
    vert
    0.07
     pursuant
    0.07
     бÑĥлÑĮ
    0.07
    æĪĸ以åħ¶ä»ĸæĸ¹å¼ı
    0.06
    lia
    0.06
    äºĨ解åĴĮ
    0.06
     hereby
    0.06
    个æĪĸå¤ļ个
    0.06
    äºĭæķħçļĦåıijçĶŁ
    0.06
    Activations Density 0.158%

    No Known Activations