© 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. 32227
    Prev
    Next
    INDEX
    Explanations

    acidic solutions

    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
    etten
    -0.07
     envol
    -0.07
     اÙĦØŃسÙĨ
    -0.07
    ibert
    -0.07
    ÑĦÑĥ
    -0.07
    леÑĨ
    -0.07
    èĿ´èĿ¶
    -0.07
    蹬
    -0.07
    leep
    -0.07
    night
    -0.07
    POSITIVE LOGITS
    å¼Ģèĥĥ
    0.12
     acidic
    0.12
    éħ¸
    0.11
    éħ¸åĮĸ
    0.11
     acid
    0.11
     acidity
    0.10
     acids
    0.10
    éħ¸æĢ§
    0.10
    èĥĥéħ¸
    0.10
     Acid
    0.09
    Activations Density 0.071%

    No Known Activations