© 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. 18010
    Prev
    Next
    INDEX
    Explanations

    in [word start]

    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
    éªĭ
    -0.07
    å°¼äºļ
    -0.07
    uci
    -0.07
    orsche
    -0.07
    Æ°
    -0.07
    celand
    -0.07
     spontaneously
    -0.07
    åħµåº«
    -0.07
    è´°
    -0.07
    нÑı
    -0.07
    POSITIVE LOGITS
    âŃIJ
    0.07
    第ä¸ī款
    0.07
     â
    0.06
    âĿ¤ï¸ı
    0.06
    æĪijçļĦè¯Ŀ
    0.06
    elingen
    0.06
    è¿Ļä¸įä»ħ
    0.06
     ðŁij
    0.06
    indir
    0.06
    rok
    0.06
    Activations Density 0.020%

    No Known Activations