© 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. 32063
    Prev
    Next
    INDEX
    Explanations

    thiol-containing compounds

    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
    çĵ¢
    -0.08
    çŃĭ
    -0.08
    faf
    -0.07
    ession
    -0.07
    olson
    -0.07
    zat
    -0.07
    åĬĽæ±Ĥ
    -0.07
    ноÑģÑĤÑĢан
    -0.07
    èľĵ
    -0.07
     Sher
    -0.06
    POSITIVE LOGITS
     sulfur
    0.08
    ç¡«
    0.08
    ç¡«åĮĸ
    0.08
    èĥ±
    0.08
     sulf
    0.07
    çĤ¹çĿĽ
    0.07
     cyst
    0.07
    oulouse
    0.07
     thi
    0.07
    åĪ°å°¾
    0.07
    Activations Density 0.053%

    No Known Activations