© 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. 13240
    Prev
    Next
    INDEX
    Explanations

    requesting information or clarification

    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
    è®°å¾Ĺ
    -0.07
    å¾·ç½Ĺ
    -0.06
    ç¥Ŀ
    -0.06
    ä½Ĩæĺ¯å¯¹äºİ
    -0.06
    ÑĦло
    -0.06
    oops
    -0.06
     however
    -0.06
    alti
    -0.06
    æķĮ
    -0.06
    åį´
    -0.06
    POSITIVE LOGITS
    elah
    0.08
    quen
    0.08
    æĸĻçļĦ
    0.08
    à¹Ģà¸ĸà¸Ńะ
    0.08
    ander
    0.07
    ä¸Ģä¸Ŀ
    0.07
    μον
    0.07
    istics
    0.07
    è¿ĺæĺ¯æľīäºĽ
    0.07
    æĢİä¹Īæīįèĥ½
    0.07
    Activations Density 0.004%

    No Known Activations