© 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. 19480
    Prev
    Next
    INDEX
    Explanations

    check if

    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
     specified
    -0.06
    æĮĩå®ļçļĦ
    -0.06
    å¬
    -0.05
    æ³ķå¾ĭåħ³ç³»
    -0.05
    è¿ĩåįĬ
    -0.05
    èł
    -0.05
    าว
    -0.05
     поводÑĥ
    -0.05
    约å®ļçļĦ
    -0.05
    æĹłä¸º
    -0.05
    POSITIVE LOGITS
    åį³æĹ¥
    0.06
    vé
    0.06
    _screen
    0.06
    ells
    0.06
    彦
    0.06
     blo
    0.06
    åıĸèĢĮ代ä¹ĭ
    0.06
     skins
    0.05
    çŃĽæŁ¥
    0.05
    blo
    0.05
    Activations Density 0.036%

    No Known Activations