© 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. 45654
    Prev
    Next
    INDEX
    Explanations

    to be verbs and conditions

    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
    uel
    -0.08
    å¦Ĥæŀľèĥ½å¤Ł
    -0.07
    poj
    -0.07
    ä¹ĭ交
    -0.06
    åĩ¡æĺ¯
    -0.06
    /{}/
    -0.06
    å¦Ĥä¸Ģ
    -0.06
    leme
    -0.06
    ä¹ĭæīĢ以
    -0.06
    ani
    -0.06
    POSITIVE LOGITS
    æŃ¤èµ·
    0.08
    éĥ½è¡Į
    0.07
    stellingen
    0.07
    adge
    0.07
    erah
    0.07
     ensued
    0.07
    cze
    0.07
    ucker
    0.07
    ksen
    0.07
    <tool_response>
    0.07
    Activations Density 0.131%

    No Known Activations