© 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. 32487
    Prev
    Next
    INDEX
    Explanations

    ate / ide / yla

    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
    åįļæł¼
    -0.08
    داÙħ
    -0.07
    afe
    -0.07
    .jquery
    -0.07
    uges
    -0.07
    ENTI
    -0.07
    anno
    -0.07
    urang
    -0.07
    ଣ
    -0.07
    tober
    -0.07
    POSITIVE LOGITS
    ate
    0.07
     aka
    0.07
    ruz
    0.07
    ãĥ£
    0.07
    ç®Ģ称
    0.06
    åħ®
    0.06
    yla
    0.06
    ide
    0.06
    æŁ¬
    0.06
    çķĶ
    0.06
    Activations Density 0.266%

    No Known Activations