© 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. 19674
    Prev
    Next
    INDEX
    Explanations

    laws and principles

    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
     wards
    -0.06
     recieved
    -0.05
    ç«ĸèµ·
    -0.05
     focus
    -0.05
    otel
    -0.05
    ÙĪØ·
    -0.05
    recall
    -0.05
    å¹´åij³
    -0.05
    inf
    -0.05
    focus
    -0.05
    POSITIVE LOGITS
    è§Ħå¾ĭ
    0.07
    åĬĽåѦ
    0.06
    éĢ»è¾ij
    0.06
     logic
    0.06
    erno
    0.06
    æ³ķåĪĻ
    0.06
    ERN
    0.06
    åĽłç´łå½±åĵį
    0.06
     Calcul
    0.05
     gravity
    0.05
    Activations Density 0.010%

    No Known Activations