© 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. 47632
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
     selectively
    -0.08
    ske
    -0.08
    åĶı
    -0.07
    álogo
    -0.07
    rieve
    -0.07
    rieben
    -0.07
    év
    -0.07
    (optional
    -0.07
    edah
    -0.07
    लà¥įप
    -0.07
    POSITIVE LOGITS
    åıĮéĩį
    0.11
    两次
    0.10
    çļĦåıĮéĩį
    0.10
    两éĥ¨
    0.09
    å¤ļéĩį
    0.09
    åıĮåĢį
    0.09
    è¿Ļ两
    0.09
     combine
    0.09
    æĢ»åħ±
    0.09
    two
    0.08
    Activations Density 0.039%

    No Known Activations