© 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. 42910
    Prev
    Next
    INDEX
    Explanations

    thoughts and thinking

    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
    redentials
    -0.08
    ãģ£ãģ·
    -0.07
    criptor
    -0.07
     prezi
    -0.07
    -ts
    -0.07
    _eof
    -0.07
    CLAIM
    -0.07
    _subplot
    -0.07
    jev
    -0.07
    æĬĢæľ¯è¦ģæ±Ĥ
    -0.07
    POSITIVE LOGITS
     thoughts
    0.13
    thought
    0.12
    æĥ³çĿĢ
    0.11
    æĢĿèĢĥ
    0.11
    Thought
    0.11
    æĥ³çļĦ
    0.11
     thought
    0.10
     Thoughts
    0.10
     Thought
    0.10
    æĢĿ
    0.10
    Activations Density 0.171%

    No Known Activations