© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 7285
    Prev
    Next
    INDEX
    Explanations

    deep venous thrombosis / post-traumatic / alpha1 / granulocyte / giant cell

    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
    Insensitive
    -0.07
    ISTI
    -0.07
    รวà¸ĩ
    -0.07
    USTA
    -0.07
    èĥ§
    -0.07
    èĶ¼
    -0.06
    еÑĤÑĮ
    -0.06
    åįİéĺ³
    -0.06
    kat
    -0.06
    .isBlank
    -0.06
    POSITIVE LOGITS
    ä¸įèĥľ
    0.08
     appunto
    0.07
    लिà¤ı
    0.07
    iá»ģm
    0.07
     Stéph
    0.07
    téri
    0.07
    å¿ĥ缮ä¸ŃçļĦ
    0.06
    iop
    0.06
     Fucking
    0.06
    ième
    0.06
    Activations Density 0.483%

    No Known Activations