© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 13901
    Prev
    Next
    INDEX
    Explanations

    orders of magnitude

    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
    leos
    -0.08
    dar
    -0.08
    zkod
    -0.08
    intage
    -0.08
    ecer
    -0.08
    моно
    -0.07
    urator
    -0.07
    ocere
    -0.07
    füh
    -0.07
     imprescind
    -0.07
    POSITIVE LOGITS
    —from
    0.08
    ondissement
    0.06
    çļĦäºĭåĦ¿
    0.06
     orders
    0.06
     Orders
    0.06
    éģķãģĨ
    0.06
    大åħ³
    0.06
     Ùħرات
    0.06
    åľ°ä»İ
    0.06
     hist
    0.06
    Activations Density 0.010%

    No Known Activations