© 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. 26999
    Prev
    Next
    INDEX
    Explanations

    supposed/purported

    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
    ä¸Ĭæ·»
    -0.08
    åıªè¦ģä½ł
    -0.08
    phem
    -0.08
    sev
    -0.07
    rawat
    -0.07
    è¾ij
    -0.07
    (raw
    -0.07
    ersi
    -0.07
    輯
    -0.07
    ewire
    -0.07
    POSITIVE LOGITS
     would
    0.12
    would
    0.11
     würde
    0.09
     Would
    0.09
     müsste
    0.08
     purported
    0.08
    å¿ħé¡»åħ·å¤ĩ
    0.07
     supposedly
    0.07
    Would
    0.07
     supposed
    0.07
    Activations Density 0.011%

    No Known Activations