© 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. 39824
    Prev
    Next
    INDEX
    Explanations

    3D printing

    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
    æ¸ł
    -0.09
    ä½
    -0.08
    ackets
    -0.07
    çħŀ
    -0.07
     CSRF
    -0.07
     Rodgers
    -0.07
     Vaughan
    -0.07
    æ°Ľ
    -0.07
    æĹłåĬŁ
    -0.07
    å¼¹çIJ´
    -0.07
    POSITIVE LOGITS
    oxel
    0.10
     voxel
    0.10
     sculpt
    0.09
    precision
    0.08
     precision
    0.08
     Precision
    0.08
    ulpt
    0.08
    Precision
    0.08
     laser
    0.08
     Ultim
    0.08
    Activations Density 0.086%

    No Known Activations