© 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. 28966
    Prev
    Next
    INDEX
    Explanations

    emails, URLs, and specific words

    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
    มà¸Ļ
    -0.09
    è´¯
    -0.08
    ìĸ¸
    -0.08
    uis
    -0.08
    aksin
    -0.08
     ве
    -0.07
    دÙħ
    -0.07
     ÑģÑĤаÑĢи
    -0.07
    çĦ¶å¤§
    -0.07
    mf
    -0.07
    POSITIVE LOGITS
    ¬ģ
    0.06
    éģ½
    0.06
    arren
    0.06
     Vitt
    0.06
    ensitive
    0.06
    ÛĮع
    0.06
    åłĤ
    0.06
    verages
    0.06
    äºĨä¸įèµ·
    0.06
    STIT
    0.05
    Activations Density 0.138%

    No Known Activations