© 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. 19099
    Prev
    Next
    INDEX
    Explanations

    case when, nth, low, log, time, http, data

    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
    æģ¯
    -0.07
    /components
    -0.06
    azzo
    -0.06
    éģĵçIJĨ
    -0.06
     Shope
    -0.06
     ly
    -0.06
     razie
    -0.06
    зÑı
    -0.06
    lop
    -0.06
    èģļ
    -0.06
    POSITIVE LOGITS
    ä¹ĭ以
    0.08
    çĹħæĥħæııè¿°
    0.08
    æľ¬äººåľ¨
    0.07
    åIJįåī¯
    0.07
    æľ¬èº«å°±
    0.07
     themselves
    0.07
     intelekt
    0.07
    εδ
    0.07
    got
    0.07
    ä¹ĭäºİ
    0.07
    Activations Density 0.062%

    No Known Activations