© 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. 18352
    Prev
    Next
    INDEX
    Explanations

    place names or specific locations

    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
    ç»Ļ对æĸ¹
    -0.06
    ikka
    -0.06
     rather
    -0.06
    xA
    -0.06
    гни
    -0.06
    xa
    -0.06
    jähriger
    -0.06
    ัà¹Īà¸Ļ
    -0.05
     finn
    -0.05
     Dunkel
    -0.05
    POSITIVE LOGITS
    é¢IJ
    0.06
    ulet
    0.05
    çŁ¥éģĵ
    0.05
     заÑħ
    0.05
    åĨħ涵
    0.05
    achs
    0.05
    à¹Ģà¸Ķà¸Ĭ
    0.05
    arem
    0.05
    raw
    0.05
     Ng
    0.05
    Activations Density 0.022%

    No Known Activations