© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 16972
    Prev
    Next
    INDEX
    Explanations

    is a

    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
    иÑĩ
    -0.06
    boro
    -0.06
     never
    -0.06
    illos
    -0.06
    ok
    -0.06
    ä¹Łåıª
    -0.05
    robe
    -0.05
    åıªåľ¨
    -0.05
     exc
    -0.05
    utzt
    -0.05
    POSITIVE LOGITS
    vi
    0.06
    US
    0.05
    onal
    0.05
    å±Ĥ
    0.05
    çĦķçĦ¶
    0.05
    ç«ĭ马
    0.05
    ussels
    0.05
    ale
    0.05
    pg
    0.05
    æł¸
    0.05
    Activations Density 0.035%

    No Known Activations