© 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. 45663
    Prev
    Next
    INDEX
    Explanations

    Read More

    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
    alap
    -0.08
    åħīåįİ
    -0.08
    ä¸ĥæĹ¥
    -0.07
    adeira
    -0.07
    erden
    -0.07
    éļ¾åħį
    -0.07
     staples
    -0.07
     STUDI
    -0.07
    oine
    -0.07
     %+
    -0.07
    POSITIVE LOGITS
    çľº
    0.07
    ying
    0.07
    PropertyDescriptor
    0.06
    ella
    0.06
    çIJĬ
    0.06
    uar
    0.06
    orius
    0.06
    è©£
    0.06
    nia
    0.06
    uste
    0.06
    Activations Density 0.002%

    No Known Activations