© 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. 19657
    Prev
    Next
    INDEX
    Explanations

    a different tact

    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
    h
    -0.06
    -0.06
     h
    -0.05
    st
    -0.05
    -
    -0.05
    çĶ±äºİ
    -0.05
    è¡
    -0.05
     atr
    -0.05
     at
    -0.05
    æĶ¯
    -0.05
    POSITIVE LOGITS
    æ¯Ķçħ§
    0.10
    对æłĩ
    0.10
    模仿
    0.10
    åıĤçħ§
    0.10
    åĢŁéī´
    0.10
     semelh
    0.09
    仿
    0.09
    类似äºİ
    0.09
     reminiscent
    0.09
    éĥ½åĥı
    0.09
    Activations Density 0.111%

    No Known Activations