© 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. 57877
    Prev
    Next
    INDEX
    Explanations

    public class, interface, abstract

    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
    èĩªå·±è¢«
    -0.08
    èĩªå·±åľ¨
    -0.07
    varo
    -0.07
    å®īè¾¾
    -0.07
    ugh
    -0.07
    aci
    -0.07
     yourselves
    -0.07
    åľ¨è®¾è®¡
    -0.06
    èĩªå·±çļĦ人çĶŁ
    -0.06
    æĪİ
    -0.06
    POSITIVE LOGITS
    astia
    0.07
    unction
    0.07
    æľīå¦Ĥ
    0.07
    ]>
    0.07
    oyo
    0.06
    为éļ¾
    0.06
    ếc
    0.06
    à¹Ĥà¸Ĭ
    0.06
    ru
    0.06
    åºĶè¿IJ
    0.06
    Activations Density 0.375%

    No Known Activations