© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 39551
    Prev
    Next
    INDEX
    Explanations

    sequences ending in 1

    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
    ahnya
    -0.07
    ÃīM
    -0.07
    tran
    -0.07
    ERING
    -0.06
    names
    -0.06
    ered
    -0.06
    es
    -0.06
    aner
    -0.06
    еÑĤки
    -0.06
    ами
    -0.06
    POSITIVE LOGITS
    psilon
    0.10
    åŃIJä¸Ĭ
    0.09
    åŃIJçļĦ
    0.08
    ç¼Ī
    0.07
    æ¿®
    0.07
    ocere
    0.07
    åĪ¶ä½ľäºĨ
    0.07
    iful
    0.07
    ²
    0.07
    à¥Ĥस
    0.07
    Activations Density 0.003%

    No Known Activations