© 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. 46187
    Prev
    Next
    INDEX
    Explanations

    are you

    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
    uarte
    -0.09
    ezo
    -0.08
    åĬĥ
    -0.08
    zerbai
    -0.08
     поÑģлÑĥ
    -0.08
    åĭĩå¾Ģ缴åīį
    -0.08
    èµģ
    -0.08
    arit
    -0.08
     asta
    -0.08
    cargo
    -0.08
    POSITIVE LOGITS
    0.06
    ovas
    0.06
     the
    0.06
    被åĪĹåħ¥
    0.06
    被æİĪäºĪ
    0.06
    ı
    0.06
    æĻ®éĢļ
    0.06
    被
    0.06
     **
    0.05
    æŁIJ
    0.05
    Activations Density 0.731%

    No Known Activations