© 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. 22517
    Prev
    Next
    INDEX
    Explanations

    cleavage or bond breaking

    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
    chwitz
    -0.08
    足äºĨ
    -0.08
    åIJįèĥľ
    -0.07
    á»ijc
    -0.07
    quan
    -0.07
     '\'
    -0.06
     covers
    -0.06
    ä¾µçķ¥
    -0.06
    à¸ģาย
    -0.06
    mada
    -0.06
    POSITIVE LOGITS
    æĸŃè£Ĥ
    0.11
    è£Ĥ
    0.09
    plits
    0.09
    æĭĨåĪĨ
    0.08
    (split
    0.08
    break
    0.08
     rupture
    0.08
    klink
    0.08
     splitting
    0.08
     dissoci
    0.08
    Activations Density 0.011%

    No Known Activations