© 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. 2866
    Prev
    Next
    INDEX
    Explanations

    followed by punctuation

    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
    ânia
    -0.08
     thiêng
    -0.08
    urch
    -0.07
    atica
    -0.07
    lesh
    -0.07
    è¯ķæĥ³
    -0.07
    ÙģØ´
    -0.07
    nhof
    -0.07
    proper
    -0.07
    uin
    -0.07
    POSITIVE LOGITS
    orda
    0.07
    য়à§ĩ
    0.06
    缮
    0.06
    ê¸ī
    0.06
     strain
    0.06
     demean
    0.06
    æ
    0.06
     phi
    0.06
    æı£
    0.06
    yv
    0.06
    Activations Density 0.004%

    No Known Activations