© 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. 38281
    Prev
    Next
    INDEX
    Explanations

    what is

    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
    æ²ĥ
    -0.07
    éĸ²
    -0.07
    è±
    -0.06
    OM
    -0.06
    ÙĦÙĬÙģ
    -0.06
    omi
    -0.06
    ome
    -0.06
    æľĢ好çļĦ
    -0.06
     port
    -0.06
    æ¾Ħ
    -0.06
    POSITIVE LOGITS
    è¯´ä½ł
    0.11
    说èĩªå·±
    0.10
    nP
    0.08
     اÙĦÙħؤ
    0.08
    说她
    0.08
    .argument
    0.07
     Pantal
    0.07
    altet
    0.07
    说ä»ĸ
    0.07
    راÙħ
    0.07
    Activations Density 0.001%

    No Known Activations