© 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. 18708
    Prev
    Next
    INDEX
    Explanations

    quotes and addresses by name

    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
    urge
    -0.07
    hias
    -0.07
    人被
    -0.06
    主é¢ĺåħļ
    -0.06
     ê¸
    -0.06
    å°Ĩ对
    -0.06
    æĬĬéĤ£
    -0.06
    ì¤į
    -0.06
    íĥ
    -0.06
    estens
    -0.06
    POSITIVE LOGITS
    aps
    0.06
    rik
    0.05
     anda
    0.05
    çĮĽ
    0.05
     Gener
    0.05
    çijŀ
    0.05
    çĿ«æ¯Ľ
    0.05
     Korn
    0.05
    ugal
    0.05
    H
    0.05
    Activations Density 0.009%

    No Known Activations