© 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. 19517
    Prev
    Next
    INDEX
    Explanations

    segments, encoding, quantile, struct

    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
    åĮĸåѦ
    -0.05
    âĢ
    -0.05
    计ç®Ĺ
    -0.05
    ä¸įç¦ģ
    -0.05
    ivor
    -0.05
     unofficial
    -0.05
    Âł
    -0.05
    chnitt
    -0.05
     ex
    -0.05
    æ»
    -0.05
    POSITIVE LOGITS
    é«ĺéĢŁ
    0.06
    _segments
    0.06
    ampa
    0.06
    unger
    0.06
    urst
    0.06
    _sequences
    0.06
    mere
    0.06
    impat
    0.06
     :,
    0.06
     segments
    0.06
    Activations Density 0.013%

    No Known Activations