© 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. 44938
    Prev
    Next
    INDEX
    Explanations

    bond lengths and types

    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
    ieux
    -0.08
    ients
    -0.07
    å¼ĢéĺĶ
    -0.07
    çĴĢ
    -0.07
    eces
    -0.07
    å¯Ĵæ°Ķ
    -0.07
    åħ¨éĽĨ
    -0.07
     sensit
    -0.07
    vak
    -0.07
    符åIJĪè¦ģæ±Ĥ
    -0.06
    POSITIVE LOGITS
     bonds
    0.09
     bond
    0.09
    bond
    0.08
     strength
    0.08
     Bonds
    0.08
    强度é«ĺ
    0.07
    å¤įåIJĪ
    0.07
    ç½ijåıĭè¯Ħ论
    0.07
     Bond
    0.07
     fusion
    0.07
    Activations Density 0.003%

    No Known Activations