© 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. 4137
    Prev
    Next
    INDEX
    Explanations

    particle phase extraction

    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
     подлежиÑĤ
    -0.08
     LABOR
    -0.07
    æī¾åĪ°èĩªå·±
    -0.07
    Įĵ
    -0.07
     earns
    -0.07
    _DESCRIPTOR
    -0.07
    ãĤ¦ãĤ¹
    -0.07
    åħįäºİ
    -0.07
    requires
    -0.07
     подлежа
    -0.07
    POSITIVE LOGITS
    ä½ľçĶ¨äºİ
    0.09
    ä¸į足以
    0.09
    温æŁĶ
    0.09
    èĥ½å¤Łå¯¹
    0.08
    足以
    0.08
     воздей
    0.08
    çݯå¢ĥ
    0.08
    对被
    0.08
    温æŁĶçļĦ
    0.08
    对幼åĦ¿
    0.08
    Activations Density 0.154%

    No Known Activations