© 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. 14014
    Prev
    Next
    INDEX
    Explanations

    sequence of numbers or characters

    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
    onders
    -0.07
    è¦ģä¹Īæĺ¯
    -0.07
    iona
    -0.07
    è¦ģä¹Ī
    -0.07
    DOMNode
    -0.06
    edo
    -0.06
    _MAPPING
    -0.06
    lis
    -0.06
    anti
    -0.06
     EITHER
    -0.06
    POSITIVE LOGITS
    åĴĮåIJĪä½ľ
    0.07
    æ·±åĮĸæĶ¹éĿ©
    0.07
    人æ°Ķ
    0.07
    Penn
    0.07
    èĵ¬èݱ
    0.07
    /php
    0.07
    inii
    0.07
    .soft
    0.07
    zier
    0.07
    ä¹Łæľī人
    0.07
    Activations Density 0.028%

    No Known Activations