© 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. 23686
    Prev
    Next
    INDEX
    Explanations

    lists like example, Lug, Asher

    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
    enh
    -0.08
    继ç»Ńéĺħ读
    -0.08
    æľīæĽ´
    -0.07
    å½±å±ķ
    -0.07
    èĥģ
    -0.07
    ile
    -0.07
    娥
    -0.07
    è°Īè¯Ŀ
    -0.06
    শ
    -0.06
    è¦ģ继ç»Ń
    -0.06
    POSITIVE LOGITS
    ç²Ĺçķ¥
    0.08
     example
    0.07
    lug
    0.07
    example
    0.07
    è¯ķè¯ķ
    0.07
    asher
    0.07
    米左åı³
    0.07
     *:
    0.07
    çĶ»ä¸Ĭ
    0.07
    ingk
    0.06
    Activations Density 0.012%

    No Known Activations