© 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. 23658
    Prev
    Next
    INDEX
    Explanations

    agent, referee, dealer, executive, selector

    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
    omic
    -0.07
    åĸĥ
    -0.07
    åįłåħ¬åı¸
    -0.07
    otis
    -0.07
    abwe
    -0.07
    SNS
    -0.07
    åįķ人
    -0.07
    aul
    -0.07
    mine
    -0.07
    liance
    -0.06
    POSITIVE LOGITS
    è¿IJçŃ¹
    0.08
    仲è£ģ
    0.08
    caster
    0.08
    åĮĹè¾°
    0.08
     mest
    0.08
     overseeing
    0.07
     matchmaking
    0.07
    iams
    0.07
    åħ¬æŃ£
    0.07
    ä¸Ńä»ĭ
    0.07
    Activations Density 0.424%

    No Known Activations