© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19484
    Prev
    Next
    INDEX
    Explanations

    Making recipes

    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
    ably
    -0.05
    åIJ«æľī
    -0.05
    angel
    -0.05
    éĻĢ
    -0.05
    å¼
    -0.05
    uke
    -0.05
    ãģĵãģ¨ãģ§ãģĹãĤĩãģĨ
    -0.05
    ÙĪÛĮÛĮ
    -0.05
     Opr
    -0.05
    æĤĶ
    -0.05
    POSITIVE LOGITS
    ãģ¦ãĤĭ
    0.06
     muta
    0.06
    åĪ©äºļ
    0.06
    éĩįè¦ģäºĨ
    0.06
    spots
    0.05
    æľīä¸Ń
    0.05
    hto
    0.05
    æłĩåĩĨ为
    0.05
    人æĹł
    0.05
    spot
    0.05
    Activations Density 0.001%

    No Known Activations