© 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. 41636
    Prev
    Next
    INDEX
    Explanations

    court of appeals, campaign, deficiencies, self-employed, Louder, brain

    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
     scop
    -0.06
    åĪ°å°¾
    -0.06
    ome
    -0.06
    ottes
    -0.06
     Dix
    -0.06
    翼翼
    -0.06
    çĶŁæ´»åľĪ
    -0.06
     MartÃŃnez
    -0.06
    âĢij
    -0.06
    ESIS
    -0.06
    POSITIVE LOGITS
    istro
    0.08
    etton
    0.07
    uels
    0.07
    orius
    0.07
    éĤ£ä¸Ģ
    0.07
    lian
    0.07
    artal
    0.07
    elui
    0.07
    wany
    0.07
    ipel
    0.07
    Activations Density 0.499%

    No Known Activations