© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 11850
    Prev
    Next
    INDEX
    Explanations

    inherent properties

    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
    berg
    -0.07
    çļĦæĦıè§ģ
    -0.07
    æľŁéĻIJåĨħ
    -0.07
    kowski
    -0.07
    à¸Ľà¸Ľ
    -0.07
    avourites
    -0.07
    eke
    -0.07
    áĥķáĥľ
    -0.07
     kans
    -0.07
    åĶĨ
    -0.07
    POSITIVE LOGITS
    èĢĮæĺ¯åĽłä¸º
    0.09
    æĺ¯åħ¶
    0.09
    çŁ¥åħ¶
    0.09
     inherent
    0.07
     Unique
    0.07
    -indent
    0.07
     unique
    0.07
    æŃ£æĺ¯åĽłä¸º
    0.07
     property
    0.07
    çĭ¬çī¹
    0.07
    Activations Density 0.021%

    No Known Activations