© 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. 22213
    Prev
    Next
    INDEX
    Explanations

    publishers and locations

    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
    æĺ¯éĿŀ
    -0.09
    ":"","
    -0.08
     Leverkus
    -0.08
    ÛĮÙĦÛĮ
    -0.07
    usra
    -0.07
    dsa
    -0.07
    æľ¬ç«ĻåĨħ容
    -0.07
    çĿ
    -0.07
    andat
    -0.07
    razil
    -0.07
    POSITIVE LOGITS
    御
    0.07
     nanti
    0.06
    ør
    0.06
    å®ŀåĬĽ
    0.06
    åģ¶éģĩ
    0.06
    ä¸Ģæĥ³åĪ°
    0.06
    åľ¨çľĭåĪ°
    0.06
    OMB
    0.06
    werk
    0.06
    åĨ¶
    0.06
    Activations Density 0.062%

    No Known Activations