© 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. 58414
    Prev
    Next
    INDEX
    Explanations

    death and loss

    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»ĭ
    -0.08
    çĭIJ
    -0.07
    éĢĥè·ij
    -0.07
    æĻķ
    -0.07
    ä¼łä¸ĸ
    -0.06
    è²ī
    -0.06
    åĪ¸
    -0.06
    éĩİå¿ĥ
    -0.06
    åĨħå¤ĸ
    -0.06
     khoán
    -0.06
    POSITIVE LOGITS
    æĤ²çĹĽ
    0.16
     mourning
    0.14
     loss
    0.13
     grieving
    0.13
     mourn
    0.13
    æĤ¼å¿µ
    0.13
    çļĦæįŁå¤±
    0.12
    Loss
    0.12
     Loss
    0.12
     grief
    0.12
    Activations Density 0.463%

    No Known Activations