© 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. 63221
    Prev
    Next
    INDEX
    Explanations

    chemical formulas and equations

    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
    çŀĴ
    -0.07
    æĥij
    -0.07
    çŀ
    -0.07
    åħ±äº§
    -0.06
    离
    -0.06
    herr
    -0.06
    asca
    -0.06
    ׳×Ļת
    -0.05
    åıijå¸ĥäºİ
    -0.05
    ux
    -0.05
    POSITIVE LOGITS
    ceaux
    0.08
    sWith
    0.08
    .detect
    0.08
    otar
    0.08
    家æķĻ
    0.08
    othe
    0.07
    oth
    0.07
    .Ultra
    0.07
    ikal
    0.07
    haj
    0.07
    Activations Density 0.270%

    No Known Activations