© 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. 47936
    Prev
    Next
    INDEX
    Explanations

    gradients and relative differences

    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
    åĬłæ·±
    -0.08
    æ·±åħ¥
    -0.08
    æ·±åħ¥åĪ°
    -0.08
    缨
    -0.08
    back
    -0.07
    æ·±åħ¥åŁºå±Ĥ
    -0.07
     Zut
    -0.07
    uas
    -0.07
    æ·±åħ¥çļĦ
    -0.07
     deepest
    -0.07
    POSITIVE LOGITS
    å¼ķåĬĽ
    0.07
    äºİæĺ¯å°±
    0.07
    çĽ¸å¯¹çļĦ
    0.07
    æ´¼
    0.07
     sucker
    0.07
    elin
    0.07
    梯度
    0.07
     gradients
    0.07
     relative
    0.07
     imbalance
    0.07
    Activations Density 0.009%

    No Known Activations