© 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. 15984
    Prev
    Next
    INDEX
    Explanations

    conditional logic clauses

    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
    _NB
    -0.08
    wyż
    -0.07
     apprec
    -0.07
    igg
    -0.07
     sahab
    -0.07
    eva
    -0.07
    å·®ä¸į
    -0.07
    леÑģ
    -0.07
    ante
    -0.06
     Lauderdale
    -0.06
    POSITIVE LOGITS
    ä¸ĢæŦåıijçİ°
    0.08
    åı«
    0.08
    Either
    0.08
    ä¸Ģç»ıåıijçİ°
    0.08
     Either
    0.08
     either
    0.07
    å¦Ĥæŀľåľ¨
    0.07
    æĬijæĪĸ
    0.07
    å¤ĩ
    0.07
    ä¸Ģå¾ĭ
    0.07
    Activations Density 0.016%

    No Known Activations