© 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. 22112
    Prev
    Next
    INDEX
    Explanations

    packaging and distribution

    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
    æĢ»æĶ¯
    -0.06
    å£ģ纸
    -0.06
    仪
    -0.06
    olz
    -0.06
    æĶ¯éħį
    -0.05
     Gust
    -0.05
    å¼ĢæĶ¯
    -0.05
    fore
    -0.05
    eline
    -0.05
    instr
    -0.05
    POSITIVE LOGITS
     Republic
    0.05
    éĽĢ
    0.05
    象
    0.05
    empl
    0.05
    ØŃÙĪÙĦ
    0.05
    åħ³äºİ
    0.05
    emers
    0.05
     riusciti
    0.05
     Asian
    0.05
    argin
    0.05
    Activations Density 0.075%

    No Known Activations