© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18696
    Prev
    Next
    INDEX
    Explanations

    products and equipment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Âł
    -0.07
    -0.06
    اطر
    -0.05
    åĮ¹
    -0.05
     ving
    -0.05
    å®īæħ°
    -0.05
     ze
    -0.05
    aged
    -0.05
     distinctly
    -0.04
     Saints
    -0.04
    POSITIVE LOGITS
    ynı
    0.06
     Kdy
    0.06
    noinspection
    0.06
    éĨį
    0.06
     induction
    0.06
    atra
    0.06
    äºĭåīį
    0.06
     |_
    0.06
    æĪĸå¤ļ
    0.06
     Enums
    0.06
    Activations Density 0.001%

    No Known Activations