© 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. 48845
    Prev
    Next
    INDEX
    Explanations

    chemistry

    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
    ами
    -0.08
    æĶĺ
    -0.08
    æ²»å®ī
    -0.08
    amen
    -0.08
    edly
    -0.07
    çĥĪæĹ¥
    -0.07
    vel
    -0.07
    ingo
    -0.07
    stitut
    -0.07
    anh
    -0.07
    POSITIVE LOGITS
    istry
    0.08
     Nobel
    0.07
    ivate
    0.07
    ع
    0.07
    nip
    0.06
    æĹłç©·
    0.06
     물ìĿĦ
    0.06
     TRAS
    0.06
    osz
    0.06
    ria
    0.06
    Activations Density 0.006%

    No Known Activations