© 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. 29643
    Prev
    Next
    INDEX
    Explanations

    Blatz, antibiotic, lag

    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
    çĦ¼ãģį
    -0.07
    踢
    -0.07
    lici
    -0.07
    çĴ¨
    -0.06
    opian
    -0.06
    ade
    -0.06
    å®īåĪ©
    -0.06
     Hidal
    -0.06
    ajak
    -0.06
    arshal
    -0.06
    POSITIVE LOGITS
    è¾ķ
    0.08
     Boone
    0.08
    ysi
    0.07
    æĦ
    0.07
    Verse
    0.07
    vs
    0.07
    Blo
    0.07
    çĭ±
    0.06
    ä½ĵå¤ĸ
    0.06
    verse
    0.06
    Activations Density 0.068%

    No Known Activations