© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19704
    Prev
    Next
    INDEX
    Explanations

    fully licensed or qualified

    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
    -0.08
    Pure
    -0.06
     Pure
    -0.06
    pure
    -0.06
     pure
    -0.06
    à¹ģห
    -0.06
    rror
    -0.06
    ILT
    -0.05
    纯æ´ģ
    -0.05
    纯
    -0.05
    POSITIVE LOGITS
    ä¸Ģ线
    0.06
    ippers
    0.06
     atrav
    0.06
    æŃ·
    0.05
    åİĨåİĨ
    0.05
    angan
    0.05
     jok
    0.05
     readily
    0.05
    ulée
    0.05
    day
    0.05
    Activations Density 0.004%

    No Known Activations