© 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. 12698
    Prev
    Next
    INDEX
    Explanations

    negative values and positive values

    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
    ierz
    -0.08
     naudo
    -0.08
    tar
    -0.07
    ä»İåħ¶
    -0.07
    åħ¶è§ĤçĤ¹
    -0.07
    #import
    -0.07
    天æĺŁ
    -0.07
    нг
    -0.07
    iero
    -0.07
    ä¹ĭçĶ¨
    -0.07
    POSITIVE LOGITS
    表æĺİ
    0.07
    olec
    0.07
    oo
    0.07
     implying
    0.06
    chet
    0.06
    fällig
    0.06
    ffet
    0.06
    à¸ļ
    0.06
    иво
    0.06
     indicating
    0.06
    Activations Density 0.002%

    No Known Activations