© 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. 31524
    Prev
    Next
    INDEX
    Explanations

    references to literature

    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
    á»ĭp
    -0.07
    çļĦçī¹çĤ¹æĺ¯
    -0.07
    indir
    -0.07
    羨
    -0.07
    éĢļè¿ĩå¼Ģå±ķ
    -0.06
    çĻ½éĵ¶
    -0.06
    uhn
    -0.06
    çĭ¬ç«ĭèĩªä¸»
    -0.06
    CanBe
    -0.06
    combe
    -0.06
    POSITIVE LOGITS
    èµ·è§ģ
    0.10
    çļĦ話
    0.09
    æľĢä½³
    0.08
    æľĢä½³çļĦ
    0.08
    æĪijçļĦè¯Ŀ
    0.08
    pls
    0.07
    æľ¬
    0.07
    «
    0.07
    etails
    0.07
     siehe
    0.07
    Activations Density 0.324%

    No Known Activations