© 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. 57698
    Prev
    Next
    INDEX
    Explanations

    solvents, separation, mixture, apparatus

    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
    ëŀŃ
    -0.09
    zaam
    -0.08
    OrFail
    -0.08
    RAL
    -0.08
    ãĥ¬ãĤ¹ãĥĪ
    -0.08
     altrett
    -0.08
    eret
    -0.08
    妥å½ĵ
    -0.08
     bÃło
    -0.08
    appropri
    -0.08
    POSITIVE LOGITS
    æ··åIJĪçī©
    0.08
     mix
    0.07
    aze
    0.07
     Emerson
    0.07
    æ··åIJĪ
    0.07
    沸çĤ¹
    0.07
    ander
    0.06
     mixture
    0.06
    ä¸įåĪĨ
    0.06
    HOR
    0.06
    Activations Density 0.001%

    No Known Activations