© 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. 16415
    Prev
    Next
    INDEX
    Explanations

    conversion into liquid or chemical products

    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
    oure
    -0.08
    ä¸įåĪĨ
    -0.07
    æ¸ħæ¸ħ
    -0.07
    ä¸įåĪ°
    -0.07
     getSource
    -0.07
    obat
    -0.07
    浴室
    -0.07
     aspekt
    -0.06
    æºIJ
    -0.06
    æĥħ人
    -0.06
    POSITIVE LOGITS
    è´®èĹı
    0.08
    åı¯ä¸º
    0.08
    nect
    0.07
     recién
    0.07
    å±Ĥå±Ĥ
    0.07
    ä¿ĿåŃĺ
    0.07
    æĸ°é«ĺ
    0.07
     localVar
    0.07
     storing
    0.07
    ellular
    0.07
    Activations Density 0.010%

    No Known Activations