© 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. 18275
    Prev
    Next
    INDEX
    Explanations

    searching database fields

    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
    ading
    -0.06
    raz
    -0.05
     götür
    -0.05
    erase
    -0.05
    å¸Ĥåľºç»ıæµİ
    -0.05
    kung
    -0.05
    æĭ©
    -0.05
    lands
    -0.05
    ç»ı审çIJĨ
    -0.05
    adow
    -0.05
    POSITIVE LOGITS
     Poss
    0.07
    åı¯èĥ½æĢ§
    0.07
     searchable
    0.06
    Poss
    0.06
    cea
    0.06
    arto
    0.06
    å¯Įæľī
    0.06
    æIJľç´¢
    0.06
    iors
    0.06
    emo
    0.06
    Activations Density 0.049%

    No Known Activations