© 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. 23933
    Prev
    Next
    INDEX
    Explanations

    artists and academic contexts

    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
     outstanding
    -0.08
     improvement
    -0.07
     snug
    -0.07
    é©°
    -0.07
    attu
    -0.07
     rookie
    -0.07
    è¿·ç³Ĭç³Ĭ
    -0.07
    è´´å¿ĥ
    -0.07
    åĬ±
    -0.06
    çĽĸ
    -0.06
    POSITIVE LOGITS
    æĮªçĶ¨
    0.09
     manipulated
    0.09
     textures
    0.09
     juxtap
    0.09
     surreal
    0.08
     dada
    0.08
    æ¦Ĥ念
    0.08
    VOID
    0.08
    çļĦæ¦Ĥ念
    0.08
    è´¨æĦŁ
    0.08
    Activations Density 0.180%

    No Known Activations