© 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. 51849
    Prev
    Next
    INDEX
    Explanations

    to speak of

    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
    utos
    -0.07
    èĬľ
    -0.07
    wald
    -0.07
    ctype
    -0.07
    æĥĬ天
    -0.07
    iton
    -0.07
    iom
    -0.07
    .roles
    -0.07
    çĥĺ
    -0.07
     визи
    -0.07
    POSITIVE LOGITS
     sourceMapping
    0.08
    æĦıåij³
    0.07
    ä¸įéĩįè¦ģ
    0.07
    egu
    0.07
     неÑĢа
    0.07
    ä¸įæĸ¹ä¾¿
    0.06
    è¦ģ好好
    0.06
    enti
    0.06
    æį¢ç®Ĺ
    0.06
    æĪijåıªæĺ¯
    0.06
    Activations Density 0.009%

    No Known Activations