© 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. 19142
    Prev
    Next
    INDEX
    Explanations

    the number zero or zeros

    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
    izard
    -0.09
    åħ°è¾¾
    -0.08
    gere
    -0.07
    -home
    -0.07
    á»±c
    -0.07
    wiss
    -0.07
    onge
    -0.07
    landes
    -0.07
    æľī家
    -0.07
    ared
    -0.07
    POSITIVE LOGITS
    /null
    0.08
    æľ¬åľºæ¯ĶèµĽ
    0.07
    æ³»
    0.07
    çĶŁçī©åѦ
    0.07
    krat
    0.07
    æ¿ģ
    0.07
    壮
    0.06
    uhan
    0.06
    emean
    0.06
    骼
    0.06
    Activations Density 0.006%

    No Known Activations