© 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. 16840
    Prev
    Next
    INDEX
    Explanations

    previous step/value

    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
    é£İåIJij
    -0.07
    éħį
    -0.07
    å°Ĭ
    -0.07
    毫
    -0.06
    é£İåĬĽ
    -0.06
     Madura
    -0.06
    æī«çłģåħ³æ³¨
    -0.06
    vs
    -0.06
    驾
    -0.06
    estream
    -0.06
    POSITIVE LOGITS
     previous
    0.12
     пÑĢедÑĭ
    0.11
    previous
    0.11
     earlier
    0.10
    Previous
    0.10
     vorige
    0.10
     précédent
    0.10
     Previous
    0.09
     precedente
    0.09
    .previous
    0.09
    Activations Density 0.009%

    No Known Activations