© 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. 25343
    Prev
    Next
    INDEX
    Explanations

    external inputs or transport

    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
    KeyType
    -0.07
    ennis
    -0.06
    æݨèįIJçļĦ
    -0.06
    boh
    -0.06
     renc
    -0.06
    immun
    -0.06
    ä¸Ī
    -0.06
    ستا
    -0.06
    强çĥĪæݨèįIJ
    -0.06
     ob
    -0.06
    POSITIVE LOGITS
     external
    0.11
    å¤ĸéĥ¨
    0.10
    çļĦå¤ĸéĥ¨
    0.09
     External
    0.09
    ambu
    0.08
    å²IJ
    0.08
     внеÑĪниÑħ
    0.08
    External
    0.08
     externos
    0.08
    external
    0.08
    Activations Density 0.002%

    No Known Activations