© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 21950
    Prev
    Next
    INDEX
    Explanations

    a/the before noun

    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
    éī´äºİ
    -0.06
    اب
    -0.05
     R
    -0.05
     rem
    -0.05
     thu
    -0.05
    iet
    -0.05
    chein
    -0.05
     (
    -0.05
     Cas
    -0.05
     casual
    -0.05
    POSITIVE LOGITS
    itique
    0.07
    вли
    0.06
     gesta
    0.06
    æĿ¥ãģ®
    0.06
    áŁĩ
    0.06
    izierte
    0.06
    ÙĥÙĬر
    0.06
     nutshell
    0.06
    scopes
    0.06
    ÑĢобÑĸ
    0.06
    Activations Density 0.073%

    No Known Activations