© 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. 16498
    Prev
    Next
    INDEX
    Explanations

    urls and file paths

    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
    ä¹İåħ¶
    -0.08
    ä¸ĩåį·
    -0.08
    éļ¾æ±Ĥ
    -0.07
    chel
    -0.07
    è¯´ä½ł
    -0.07
    NÄIJ
    -0.07
    erson
    -0.07
    èݱåĿŀ
    -0.07
    \Id
    -0.07
    ä¸İåħ±
    -0.07
    POSITIVE LOGITS
    ¿
    0.09
    byg
    0.07
    deen
    0.07
    itura
    0.06
    roh
    0.06
    çŃĶæ¡Ī解æŀIJ
    0.06
    ariana
    0.06
     Щ
    0.06
    örü
    0.06
    .iteritems
    0.06
    Activations Density 0.010%

    No Known Activations