© 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. 18394
    Prev
    Next
    INDEX
    Explanations

    match scores

    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
    лив
    -0.07
    lach
    -0.06
    chers
    -0.06
    iques
    -0.06
    encil
    -0.06
    ики
    -0.06
    ระหวà¹Īาà¸ĩà¸ģาร
    -0.06
    ique
    -0.05
    ÑĩиÑĤа
    -0.05
     Brace
    -0.05
    POSITIVE LOGITS
    åĽºå®ļçļĦ
    0.05
    çĻ¾å²ģ
    0.05
    assen
    0.05
     dalamnya
    0.05
    è¾
    0.05
    dez
    0.05
    åĨħ容åıĬ
    0.05
    heus
    0.05
    à¥ĭà¤Ĺ
    0.05
    åı¯è§Ĩ
    0.05
    Activations Density 0.006%

    No Known Activations