© 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. 44034
    Prev
    Next
    INDEX
    Explanations

    pro, pect, ext

    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
    erot
    -0.09
    arness
    -0.08
    abrina
    -0.08
    aisin
    -0.08
    جÙĩ
    -0.08
    ABILITY
    -0.07
    agnes
    -0.07
    rawer
    -0.07
    oom
    -0.07
    gies
    -0.07
    POSITIVE LOGITS
    amb
    0.07
    ëŁ½
    0.07
    isson
    0.06
    å¸ĥæĸ¯
    0.06
    éĹ®åıĬ
    0.06
    éľĢè¦ģåIJĮ
    0.06
    ä»Ĭ次
    0.06
    ä½ľçļĦ
    0.06
     amb
    0.06
    Vs
    0.06
    Activations Density 0.001%

    No Known Activations