© 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. 42548
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with exponents

    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
     prop
    -0.08
    prop
    -0.06
    éĤ£çīĩ
    -0.06
    PT
    -0.06
    j
    -0.06
    åį·
    -0.06
    ess
    -0.06
     Prop
    -0.06
     pros
    -0.06
     tre
    -0.06
    POSITIVE LOGITS
    hani
    0.09
    ént
    0.09
    "data
    0.08
    åħ¨éĺŁ
    0.08
    è¾
    0.08
     ménage
    0.08
    大åѦæķĻæİĪ
    0.08
    بÙĬب
    0.07
    umul
    0.07
    stät
    0.07
    Activations Density 0.004%

    No Known Activations