© 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. 9846
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and elements

    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
    abay
    -0.07
     Rubin
    -0.07
    edy
    -0.07
    ilian
    -0.07
    omain
    -0.07
    azes
    -0.07
    ardy
    -0.07
    vam
    -0.06
     nég
    -0.06
     knight
    -0.06
    POSITIVE LOGITS
     weighing
    0.09
    åIJ«ç¨İ
    0.08
    åĪĨåŃIJéĩı
    0.08
    åħ¶èº«
    0.08
     deteri
    0.07
     weighs
    0.07
    æ¯ıåħ¬æĸ¤
    0.07
    _POINTER
    0.07
    æĹ¥ä»¥
    0.07
    Prot
    0.07
    Activations Density 0.009%

    No Known Activations