© 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. 1923
    Prev
    Next
    INDEX
    Explanations

    BCR-ABL and aromatase inhibitors

    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
    èvres
    -0.08
     globally
    -0.07
     Coy
    -0.07
    åħ¨åľĭ
    -0.07
    .global
    -0.07
    lip
    -0.07
    amenti
    -0.07
    åħ¨åĽ½
    -0.07
    _COMPILER
    -0.07
    inue
    -0.07
    POSITIVE LOGITS
    éĢĤçĶ¨äºİ
    0.11
    对äºİä¸Ģ个
    0.10
    åĽłä¸ºæĺ¯
    0.10
    å¦Ĥæŀľæĺ¯
    0.09
    èĭ¥æĺ¯
    0.09
    éģ©çĶ¨æĸ¼
    0.09
    å¦ĤæŀľæĤ¨æĺ¯
    0.08
    å¦Ĥåľ¨
    0.08
    å¦Ĥæŀľä½łæĺ¯
    0.08
    对æľī
    0.07
    Activations Density 0.480%

    No Known Activations