© 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. 60389
    Prev
    Next
    INDEX
    Explanations

    cyclo- related words

    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
    ials
    -0.08
    mise
    -0.08
    mals
    -0.08
    ãĥ£
    -0.07
    lade
    -0.07
    europ
    -0.07
    æµģç»ı
    -0.07
    ÏĥÏį
    -0.07
    -know
    -0.06
    常åĬ¡å§Ķåijĺä¼ļ
    -0.06
    POSITIVE LOGITS
    lical
    0.09
    anski
    0.09
    olygon
    0.08
    chetti
    0.08
    áĢ·áĢº
    0.08
    otron
    0.08
    Õ®
    0.07
    RAFT
    0.07
    udem
    0.07
    ersistent
    0.07
    Activations Density 0.010%

    No Known Activations