© 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. 34691
    Prev
    Next
    INDEX
    Explanations

    adverse states or conditions

    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
    пÑĢинима
    -0.09
    åħ³åı£
    -0.09
    pek
    -0.09
    ÏĦÏģο
    -0.09
     пÑĢиви
    -0.09
    "%(
    -0.09
    तर
    -0.08
    erville
    -0.08
    ünft
    -0.08
    ozn
    -0.08
    POSITIVE LOGITS
    ãĢģ
    0.08
    æĪĸèĢħæľī
    0.07
    ãĢģãĢģ
    0.07
    æĪĸèĢħ
    0.07
    ↵
    0.07
    chia
    0.06
    æĪĸèĢħæĺ¯
    0.06
     ||
    0.06
    æĪĸæľī
    0.06
    èĢĮä¸Ķ
    0.06
    Activations Density 0.007%

    No Known Activations