© 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. 16994
    Prev
    Next
    INDEX
    Explanations

    Eternal Tank

    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
    èĪī
    -0.06
    oral
    -0.06
    umen
    -0.06
    øm
    -0.05
    curity
    -0.05
    uz
    -0.05
    lex
    -0.05
    aki
    -0.05
    let
    -0.05
    ilio
    -0.05
    POSITIVE LOGITS
    à¸ļà¸ļ
    0.06
    æĸ¥
    0.06
     finalist
    0.06
     Algar
    0.06
    å¦Ĥä¸Ģ
    0.06
    еÑĪе
    0.06
    åºı
    0.05
    è§Ī
    0.05
     fam
    0.05
     onStart
    0.05
    Activations Density 0.003%

    No Known Activations