© 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. 19616
    Prev
    Next
    INDEX
    Explanations

    feeling states

    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
    anno
    -0.07
    ishly
    -0.07
    ajaan
    -0.07
    ights
    -0.07
    çĦ¶æĺ¯
    -0.06
    ç»ĵæŀĦæĢ§æĶ¹éĿ©
    -0.06
     Januari
    -0.06
     '=
    -0.06
    alaman
    -0.06
    поÑĢа
    -0.06
    POSITIVE LOGITS
    åij¨ä¸ī
    0.05
     eng
    0.05
    b
    0.04
     aleg
    0.04
    ç±»
    0.04
     communicating
    0.04
    å¤Ħ
    0.04
    ì²Ļ
    0.04
     fun
    0.04
     st
    0.04
    Activations Density 0.003%

    No Known Activations