© 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. 33186
    Prev
    Next
    INDEX
    Explanations

    always or unless

    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
    dcc
    -0.08
    .retrieve
    -0.08
     Balik
    -0.08
    æĹ¥åł±
    -0.08
    -www
    -0.08
    iets
    -0.08
    ayne
    -0.08
    uddenly
    -0.08
    èĢģçĪ¹
    -0.08
    HING
    -0.08
    POSITIVE LOGITS
    éĻ¤éĿŀ
    0.14
    å¿ħçĦ¶æĺ¯
    0.13
     always
    0.13
    always
    0.13
     unless
    0.12
    å¿ħå®ļ
    0.12
    èĩ³å°ijåľ¨
    0.12
     ALWAYS
    0.12
    unless
    0.12
    å¿ħ
    0.12
    Activations Density 0.099%

    No Known Activations