© 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. 9958
    Prev
    Next
    INDEX
    Explanations

    edges, hops, or listed

    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
    akaan
    -0.08
    tdown
    -0.08
    itasi
    -0.08
    ries
    -0.08
    éĥ¨èIJ½å®¢
    -0.07
    гоÑĢе
    -0.07
     disso
    -0.07
    çī¹æľĹ
    -0.07
    éĩijé¦Ļ
    -0.07
    اء
    -0.07
    POSITIVE LOGITS
     preferably
    0.08
     alternatively
    0.07
     ideally
    0.07
    θα
    0.06
     including
    0.06
    æ´ĭ
    0.06
    è¿ĽèĢĮ
    0.06
     equival
    0.06
    æŶéĹ´èĬĤçĤ¹
    0.06
     necessarily
    0.06
    Activations Density 0.128%

    No Known Activations