© 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. 56564
    Prev
    Next
    INDEX
    Explanations

    true

    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
    å¹´ä¸ĢåŃ£åº¦
    -0.08
    æĹ¶èµ·
    -0.08
    åı«ä»Ģä¹Ī
    -0.08
    еÑĪе
    -0.08
    anitize
    -0.08
    fant
    -0.08
    年第ä¸ĢåŃ£åº¦
    -0.08
    ITHER
    -0.07
    -twitter
    -0.07
    anh
    -0.07
    POSITIVE LOGITS
    ferences
    0.07
    mel
    0.07
    kol
    0.06
    icas
    0.06
    agl
    0.06
    ichts
    0.06
    soon
    0.06
    æĩĤ
    0.06
    微信æī«ä¸Ģæī«
    0.06
    ly
    0.06
    Activations Density 0.214%

    No Known Activations