© 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. 44122
    Prev
    Next
    INDEX
    Explanations

    markdown headings

    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
    appropri
    -0.09
    ople
    -0.08
    achinery
    -0.08
    anci
    -0.08
    etti
    -0.07
    pto
    -0.07
    æ¢
    -0.07
    åħ·
    -0.07
    plusplus
    -0.07
    èĮ
    -0.07
    POSITIVE LOGITS
    ings
    0.07
     wichtigsten
    0.07
    iel
    0.07
     reasons
    0.07
    zel
    0.06
    izza
    0.06
    ãĤ¬ãĥ©
    0.06
    hil
    0.06
    yal
    0.06
    lig
    0.06
    Activations Density 0.002%

    No Known Activations