© 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. 21070
    Prev
    Next
    INDEX
    Explanations

    contrast or concession conjunctions

    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
    éĹ®åĮ»çĶŁ
    -0.08
    ืà¹Īà¸Ńà¸ĩ
    -0.07
    èij«
    -0.07
    袤
    -0.07
     RELA
    -0.07
    reb
    -0.07
    гл
    -0.07
    ieres
    -0.07
    ừa
    -0.07
    çĥ½
    -0.07
    POSITIVE LOGITS
    转èĢĮ
    0.08
    ä¸Ģ转
    0.08
     заÑĤо
    0.07
    åį´è®©
    0.07
    åģıåģı
    0.07
    ä½Ĩå½ĵ
    0.07
    ä½Ĩ对äºİ
    0.07
    转åıĺ为
    0.07
    ر
    0.07
    è½¬çľ¼
    0.06
    Activations Density 0.449%

    No Known Activations