© 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. 23975
    Prev
    Next
    INDEX
    Explanations

    black holes

    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
    ÛĮرÙĩ
    -0.07
     Caro
    -0.07
    anch
    -0.07
    secutive
    -0.07
    ضÙĬØ©
    -0.07
    ptom
    -0.07
    UAR
    -0.07
    çļĦä¸Ģ件äºĭ
    -0.07
    å¾Ĵ
    -0.06
    TVT
    -0.06
    POSITIVE LOGITS
     spin
    0.10
     Spin
    0.10
    Spin
    0.10
     spins
    0.09
    spin
    0.09
    iba
    0.09
     spinning
    0.09
    -spin
    0.08
     slashed
    0.08
     electromagnetic
    0.08
    Activations Density 0.003%

    No Known Activations