© 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. 12209
    Prev
    Next
    INDEX
    Explanations

    acidic or basic salts

    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
    aseline
    -0.08
    ISTR
    -0.08
     Trink
    -0.08
    _bundle
    -0.08
    impse
    -0.08
    å¤ĸ人
    -0.08
    åľ¨é«ĺéĢŁåħ¬è·¯
    -0.08
    upert
    -0.07
    åħ¨ç¨ĭ
    -0.07
     наб
    -0.07
    POSITIVE LOGITS
     liber
    0.09
    åIJ«æľī
    0.08
    éĺ³
    0.08
     Acid
    0.07
    æ±Łæ²³
    0.07
    ä¾ĭå¤ĸ
    0.07
    两æĢ§
    0.07
    éħ¸
    0.07
    æĹłæľº
    0.07
    ä¸įåIJ«
    0.07
    Activations Density 0.003%

    No Known Activations