© 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. 29428
    Prev
    Next
    INDEX
    Explanations

    conjunction "but" followed by clause

    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
    ate
    -0.07
    eration
    -0.07
    /or
    -0.07
     etc
    -0.07
    人
    -0.07
    ами
    -0.07
    æĺ¯
    -0.06
    ardon
    -0.06
    opher
    -0.06
    èĢĮä¸Ķæĺ¯
    -0.06
    POSITIVE LOGITS
    jenigen
    0.10
    еÑģ
    0.09
    ä¸İæѤåIJĮæŶ
    0.09
     ë§Įìķ½
    0.09
    Ĥ
    0.09
    orem
    0.09
    åıĪä¸į失
    0.08
    że
    0.08
    éľĢè¦ģ注æĦıçļĦæĺ¯
    0.08
    ellan
    0.08
    Activations Density 0.035%

    No Known Activations