© 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. 65253
    Prev
    Next
    INDEX
    Explanations

    numbers followed by years

    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
    è¿Ł
    -0.07
    kund
    -0.07
    ched
    -0.06
    èħĶ
    -0.06
    éļĶ
    -0.06
    rang
    -0.06
    æĬĢæľ¯ä¸Ĭ
    -0.06
    ché
    -0.06
    lah
    -0.06
    ä¸įåIJ«
    -0.06
    POSITIVE LOGITS
    éĹ®åĮ»çĶŁ
    0.08
    cks
    0.08
    Disabled
    0.08
    bos
    0.07
     sharper
    0.07
    wer
    0.07
    BTN
    0.07
    ckt
    0.07
    issan
    0.07
    Ĩ
    0.07
    Activations Density 0.010%

    No Known Activations