© 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. 51023
    Prev
    Next
    INDEX
    Explanations

    particle production, reactions, decay

    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
     Vend
    -0.06
    ä¸įä¸Ģ
    -0.06
    æł¹æį®éľĢè¦ģ
    -0.06
     adjustments
    -0.06
    æ¶Ĥ
    -0.06
    纵横
    -0.06
    è¿·
    -0.05
    uteur
    -0.05
     working
    -0.05
    å¯
    -0.05
    POSITIVE LOGITS
     involving
    0.10
    åĽĽä¸Ń
    0.10
    æ¶īåıĬ
    0.09
    æ¶īåıĬåĪ°
    0.09
    ׼×Ļ
    0.08
    quettes
    0.08
    ิà¸ĩ
    0.08
     directe
    0.08
    atics
    0.08
    Forbidden
    0.08
    Activations Density 0.040%

    No Known Activations