© 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. 39019
    Prev
    Next
    INDEX
    Explanations

    xml element closing tag

    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
    ä¼Ļ
    -0.09
    ölt
    -0.08
    лÑıÑĢ
    -0.08
    åĢ¶
    -0.08
    ellige
    -0.08
    bliche
    -0.08
    åĩºå£°
    -0.07
    ä¸įç»ıæĦıéĹ´
    -0.07
    arani
    -0.07
    ç£ķ
    -0.07
    POSITIVE LOGITS
    å°ī
    0.07
    rede
    0.07
    æİ¥çĿĢ
    0.06
    ç¿
    0.06
     Conc
    0.06
    append
    0.06
    èķī
    0.06
    abbo
    0.06
    è¿ijå¹³
    0.06
    ess
    0.06
    Activations Density 0.005%

    No Known Activations