© 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. 3746
    Prev
    Next
    INDEX
    Explanations

    tumor and cyst suffixes

    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
    ä¸Ģéģį
    -0.08
    æĢ¥ä¿ĥ
    -0.07
    è®
    -0.07
     Intens
    -0.07
    åĨ½
    -0.07
    æµģæĦŁ
    -0.07
     thirsty
    -0.07
     intens
    -0.07
     inputs
    -0.06
     thô
    -0.06
    POSITIVE LOGITS
     benign
    0.12
    èī¯æĢ§
    0.12
     harmless
    0.10
    缴å¾Ħ
    0.10
    ectomy
    0.10
     size
    0.10
     добÑĢо
    0.09
     solitary
    0.09
    èĤ¿åĿĹ
    0.09
    moid
    0.09
    Activations Density 0.531%

    No Known Activations